13
Nov 2023

EPIC Update: v5.1.0 Oil Machine Trading Software

Machine Trading , , , , , , , Curt Melonopoly

November 13, 2023

RE: EPIC v5.1.0 Protocol Updates –  Hard Stop Pivots & Downside Risk Management

The development team of EPIC Crude Oil $CL_F Machine Learning Software (Oildefi.io), $SPY SP500 $MES Machine Learning Software (SP500defi.io) and soon to be launched $BTC and $ETH Machine learning software have been at it for near 8 years and see the Version 5 series as a significant milestone. In future, we expect only moderate “tweak” updates to the Oil Trading Software. The others should follow in with EPIC’s Oil architecture in months – not years. 

Please refer to previous white papers and updates for historical context.

In this update we provide important information regarding (1) Hard Stop / Reversal Pivot Protocols and (2) Downside Risk Management.

(1) Hard Stop / Reversal Pivot Protocol.

Prior to the Pivot Protocol challenge, the most significant challenge our team had was the “stability” protocol, it took the longest by far to conquer. Next in complexity was the pivot protocol. At issue with pivots specifically – order fills and the age-old “death by a thousand cuts”. The software executes market orders by design per architecture – again, refer to previous white papers and updates.

The most recent downturn in crude challenged the team to find a way to avoid the pivot execution paper cut challenge. In short, we accomplished an 80% win rate at pivot executions. Previous to this period of draw-down we struggled to find a way for the software to execute in size at key pivots without taking paper cuts that added quick to downside risk. This is now mitigated through order flow tech (see IDENT references in previous papers). In short 8 in 10 executions now manifest positive return executions which is far better than 1 in 10 at pivots it was firing at previously.

For the first time reader, in short, EPIC fires at key pivots often against trend and builds a position creating a low dollar cost average on high frequency trades during a sequence of exections. At issue, was primarly our ability to have the software fire in size and not have paper cut draw downs. This is now resolved. A significant milestone.

(2) Draw-Down Mitigation.

Having the pivot / reversal execution protocol firing at 80% upside rate allows the architecture of the draw down risk component of the software to be very, very “tight”. Observers will find over the near term EPIC to remain aggresive and yet very limited in draw-down size. This was previously not possible due to the “paper-cut” issue discussed above. 

The advancements in architecture described above are considerable game changers for our development team and the holders of tokenization projects (representing returns or losses in trade) and the Sovoron.com private side client(s).

We expect ROI consistency and value to increase significantly forward.

Business Inquiries.

For information about our subscription services that include; oil trade alerts, an oil trading room and oil trade newsletter reporting contact Compound Trading Group at [email protected] or www.compoundtrading.com.

For information about the data behind the trade (results) or utilizing our automated crude oil machine trading platform contact our agent representative Richard Regan:

Email [email protected]
Phone 1-849-861-0697

Historical documents can here:

03
Jun 2023

EPIC v4.1.1 Crude Oil Machine Trade Software White Paper | June 3, 2023

Machine Trading , , , , Curt Melonopoly

EPIC v4.1.1 Crude Oil Machine Trade Software

Project History & Objective.

Our team set out over six years ago to develop sophisticated software architecture for the trade of crude oil futures.

The objective: to provide a stable yet high performance product achieving an increasingly higher ROI over time as the software processes market data, structure of trade action and order-flow.

The software has undergone a number of updates over recent years (see links at end of this document for previous white paper updates), the most recent updates have provided for a stable trading entity that continues to excel in terms of ROI.

The most recent updates, noteably the Dec 8, 2022 EPIC v3.9 update and the most recent EPIC v4.1.1 version are providing stellar real world results both in terms of ROI and stability.

EPIC is used by the trading team at Compound Trading (for live trading alert feeds and the live trading room), also by Sovoron.com for private client trading executions and OilDefi.io to facilitate a decentralized (Defi) crypto tokenization platform.

Below is a sample Sovoron real trade account performance. 

SOVORON.com 58.69% Annualized ROI from previous update to EPIC v4.1.1 software update and forward Dec 8, 2022 – June 2, 2023 (audited financials or sample account broker statements available for SOVORON participants). As of June 2, 2023 software is in its first sequence of the new v4.1.1 update and escalates protocol to a total of maximum nine sequences. Estimated ROI for this version of software is well over 100% per annum but is difficult to determine full potential through the nine sequence escalations.

Calculated using a sample 300k account (real trades) per this calculation (click here).

Sample real 300k account ROI graph.

Note the consistent trajectory with low draw down and the increased trajectory of return.

This image has an empty alt attribute; its file name is EPIC-Annualized-Trading-Results-1024x386.jpg

The primary challenge until mid 2021 was “stability” vs. ROI objectives.

Until recently, some versions of the software achieved over 150% annual ROI and some as low as 20%. The size of the trade account was the most significant determining factor (the larger the account size the more stable the software is and the higher the return).

Over time the architecture of the software has been perfected, but the real game-changer has been the development of the EPIC IDENT™ Order Flow component of the code and more recently the Intra-Day High Frequency code that relies heavily on IDENT™.

In short, there are three primary protocols of code in the software;

  1. Swing Trading (average sequence duration is 11 weeks and has been as short as 1 week and as long as 16 weeks).
  2. Intra-Day High Frequency (average sequence duration is considerably less than 24 hours but can also be described at times as intra-week lasting up to 3 or 4 days).
  3. EPIC IDENT™ Order Flow (extremely high frequency for positioning alongside significant machine “entities” that have presented themselves in the intra-day order flow). 

The software has proven to be very stable while consistently providing considerable returns. 

To our knowledge the EPIC Oil Machine Trading Software is best in class. 

EPIC Software Highlights.

  1. Lightning Fast Decisions. EPIC crude oil trading software executes trades through utilizing over 9300 weighted decisions instantly. The instructions provided within the architecture are growing daily. A human trader cannot make decisions as quickly, cannot process the data required for most intelligent trading probabilities and cannot execute trades as precisely.
  2. Algorithmic Chart Models. The EPIC software includes over thirty proprietary algorithmic chart models and the catalogue is growing. The algorithmic models have been designed, tested and refined in real-world trade for over 6 years by a team of day traders, each with over 20 years of experience. The oil trading models represent all time-frames from 15 second to monthly time-frames of trade. The algorithmic models have been back-tested to sixty months historically.
  3. Conventional Charting. The software includes conventional charting structures on all time-frames, also back-tested sixty months.
  4. Common Trade Set-Ups. Included in the software are common trade set-ups that oil day traders implement. 
  5. Order Flow. EPIC IDENT™ is data-driven order flow intelligence in real-time to achieve best outcomes. The software includes and executes to a proprietary order flow identification system that tracks behavior (specifically isolating other market machine liquidity) and weighs identified entities and historical trade patterns to its trade decisions (instructions). EPIC IDENT™ increases its intelligence as it gathers data intra-day specific to liquidity flow, historical patterns, time of day, volatility, various preferences, latency, rejects and more. The method is similar to back-testing charting. However, the process occurs in real-time. In short, the software is looking for “fingerprints” within market liquidity. We cannot back-test 60 months as with charting, but back-testing from date of software deployment has been achieved.
  6. Time Cycles. Time cycles are within all algorithmic and conventional trading model structures. Order flow also has identified time cycles and other time cycle events such as weekly reporting in oil markets (API, EIA and rig counts). Additionally there are time-of day market time cycles around the world. All of these different time-cycles are included in the software architecture.
  7. Hard-Pivot Architecture. The risk threshold – management system within the EPIC architecture now has a hard pivot rule-set that has near ended substantial risk for accounts in the 300k range and completely ended risk for the 600k or larger accounts.

Combined, these advantages enable the EPIC Crude Oil Trading software to outperform conventional trading methods.

Introduction to Oil Market Trade and Machine Trading.

The world of public market trade is rapidly changing. It is estimated (depending on source) that over 80% of crude oil futures are not traded by humans and are now traded by machines.

Machine trade may be simple, bot style software, high-frequency software or more sophisticated architecture as with the EPIC class of algorithm.

Our team commenced the oil trading software development journey nearly seven years ago with algorithmic chart model development. From day one we employed computer scientists to work with us on a daily basis to build software that would emulate our trading methods.

Over time the software started to win more trades than our traders and today we rely almost solely on the software to execute trades. We simply “tweak” the software at each trade sequence to improve performance.

Account Size – ROI and Draw-Down Volatility.

The smaller the account size traded, the more difficult it is for the software to limit downside risk and provide optimal returns.

We have learned over time that a 100k account size will see volatility and has considerable associated risk. A 300k account size will rarely see volatility (draw-down risk) and a 600k account size is expected to almost never encounter volatility. As noted above, the risk threshold – management system within the EPIC architecture now has a hard pivot rule-set that has near ended substantial risk for accounts in the 300k range and completely ended risk for the 600k or larger accounts.

The software is designed to trade within a sequence of trade within structures or set-ups. As the oil market price changes, the software trading logic uses all the different data to update the decision tree utilizing the instruction rule-set.

You can imagine this as a dot plot process similar to the game “Go” – not exactly, but the concept helps to visualize how the software plots a sequence plan for trade.

The “ebb and flow” of regular oil market trade allows opportunity for the software to plot a plan of trade within a sequence. The larger the account, the more dots that can be plotted (trades can be “bite sized” entries within an “ebb and flow”).

To understand the trading methodology of the software in each “sequence” of trade requires a moderately in-depth conversation to review data with a member of our team.

In short, the software uses a positioning (swing trade) protocol for each sequence of trade and a high-frequency intra-day protocol via EPIC IDENT™ technology. On the positioning (swing trade) side of the architecture, this means that as crude oil price is rising the software is building a position short through-out the rally (and the opposite is true if the price of oil is falling). However, the average cost is off-set by the high-frequency component of trade via EPIC IDENT™ technology so that when the trend reverses the software achieves considerable returns.

API / Deployment Architecture.

EPIC v4 software is designed to be deployed remotely – accessing an account and executing trades. This provides the account holder with ultimate control. The account holder grants the software access and the software executes machine trades to the account. Architecture provides opportunity for decentralized platform integration.

Conclusion.

This paper outlines the opportunities that can be presented by the growing influence of machine trade on global financial markets.

Competitors within the machine trade industry are becoming more and more refined and successful – the best in class are assumed to be winning a larger portion of proceeds.

The most significant immediate challenge developers face in machine trade is building a product that will perform within a prescribed threshold of downside limiting stability while outperforming conventional trading methods.

Soon thereafter the challenge becomes competing against “like-kind” machine trade peers and being best in class.

It is our expectation that fewer and fewer competitors will achieve more of the proceeds (as a whole of trade in public markets) at an exponential rate, which does provide urgency to development and deployment.

The EPIC v4 trading software achieves consistent, predictable and very adaptable architecture that provides exceptional best in class ROI.

Business Inquiries.

For information about our subscription services that include; oil trade alerts, an oil trading room and oil trade newsletter reporting contact Compound Trading Group at [email protected] or www.compoundtrading.com.

For information about the data behind the trade (results) or utilizing our automated crude oil machine trading platform contact our agent representative Richard Regan:

Email [email protected]
Phone 1-849-861-0697

Previous in this document series can be found here:

02
Feb 2020

EPIC v3 Crude Oil Code Updates: Drawdown & Short Selling Protocols $CL_F $USO #machinetrading

Machine Trading , , , , , , Curt Melonopoly

RE: EPIC v3 Crude Oil Trading Software Updates

Good afternoon traders,

It is Sunday Feb 2, 2020 and futures markets will be opening soon.

In advance of a new week I am communicating our most recent EPIC v3 code updates to keep everyone abreast of changes. I have had a number of email and DM discussions and will encapsulate the question and answer of those discussions below.

Through-out the previous trading week I did communicate much of this content below in summary form via email, in private oil trade member server on Discord and even Twitter. If you prefer the reader’s digest version see this link: https://twitter.com/curtmelonopoly/status/1223755725572378624

The EPIC v3 version software is consistently on the win side to near 100% win-rate, easily above 90% consistently. This goal was the primary challenge for us in development, without this accomplishment everything else is moot – it simply would not matter. Coding the draw-down protocol to a level of comfort is much much less work.

In short, we have coded with success an extremely high win percentage rate and that took extensive work and includes over 8700 instructions of code. This is our concrete footing.

At issue however, is when the software does lose a trade – specifically the drawdown amount.

Also at issue, and not as problematic is the win rate on the short selling side. Per previous communications we may or may not ever find success in this code and it doesn’t really affect the ROI expectations because our code protocol for drawdown on short side trades is extremely throttled so there is near zero potential loss in short trade sequences.

Specific to the drawdown percentage during a loss, the most recent white paper outlines the protocol for percentage of loss allowable here: 

White Paper Updated Dec 29, 2019: How EPIC v3 Crude Oil Machine Trading Outperforms Conventional Trading

So then the question becomes, if we know we can win easily more than 90% then why risk significant drawdown amounts when a trade does not work?

The answer or the balance of thinking is in the potential annual returns, we do not know the answer to the question – if we throttle the software to lower risk how that will affect annual returns.

We know that we can run returns 80% – 150% per year leaving the drawdown protocol as it is, but the problem is that the drawdowns are not just very uncomfortable, with smaller accounts they are more significant in terms of percentage and put at risk the account itself.

So this update is specifically motivated by and to accounts in the 10 contract size category or less, although updates to the code are in effect for all size of accounts.

So as I communicated to our clients last week we have initially throttled the software drawdown protocol to 50% of the previous protocol as outlined in the most recent white paper update (link above).

If this code update (50% of previous) is not performing as we expect we will again throttle to another 50%. I do not think this will be necessary and I am sure the current update is more than acceptable.

What does this mean in real world practical applications?

The expectations of returns are likely to be less than previously expected but this is not known until we see how the near term trade sequences perform. There is the far off chance the annual returns will actually be better than prior.

The code is throttled which manifests as only the highest probability of trade set ups to trigger a sequence, however, when a sequence starts the frequency of trade may be considerably more because the downside / stops are significantly tighter than the previous code.

In practical terms, this means that the software will not likely hold more than a 3/10 size trade for any amount of time at all unless the win side trade is extremely structured and trending up and it also means that any amount of draw-down will be limited to one quad on EPIC 30 minute model (with some slippage allowed pending order flow).

The range of trade is much smaller (limited to one quad on EPIC model or channel of the model), the size is much smaller in a sequence if there is pressure at all and the frequency of trade once it starts firing will be much higher.  

In summary, you will see the software fire predominantly per the EPIC 30 minute model weighted against all other models and order flow within a much tighter size management protocol.

It is difficult to summarize over 8700 instructions but that is my best attempt at a summary.

I encourage you to read the most recent white paper update (link above) and review the new update when released.

For those asking what I expect forward, you can expect a very tight trading protocol with higher frequency and very limited downside at any given time.

When the software gets in to a sequence that is well structured and trending you can expect the previous ROI trajectory to be returned very quickly.

Do I think that will be this week? I am not totally convinced but I wouldn’t doubt it. Structure was returning to trade on Friday and when enough structure is returned to market wide trade it won’t take the software long (as we have experienced in other drawdowns since v3 inception).

In terms of changing the throttle going forward, I wouldn’t expect us to loosen the code throttle any time soon. I know in past on a number of occasions we have discussed this and this has been a challenge for us (the balance of risk vs return). HOWEVER, I can say with utmost certainty that we are at a time in our development where risk cannot be tolerated anytime soon. 

I will be sure to communicate clearly IN ADVANCE if this is going to change in future.

To be frank we have been in development for some time and we have the winning card that we can rely on – the long side win rate that is extremely high. We were simply trying to push our development to potentially garner the largest returns possible. But reality is reality and at a certain point in time you simply have to accept where you have come and let the return rate be what it is.

Watch how the software performs over the next month and we can re-look at it at a later time. Send me your thoughts after a month or so. A month of trade executions will explain much better than I can here.

For now lets enjoy some consistent returns without the stress. 2020 will be stressful enough in the markets, we don’t need to add more.

An updated oil trade report is due out for our clients later this evening also by the way. 

Any questions please send me a note via email [email protected].

Thank you.

Curt

Further Learning:

If you would like to learn more, click here and visit our Crude Oil Trading Academy page for complimentary oil trading knowledge – posts from our top crude oil traders that includes learning systems, blog posts and videos.

Welcome to NYMEX WTI Light Sweet Crude Oil Futures.

Subscribe to Oil Trading Platform:

Standalone Oil Algorithm Newsletter (Member Charting Reports sent out weekly at times in report form or updated on email regularly).

Real-Time Oil Trading Alerts (Private Twitter feed and Discord Private Server Chat Room).

Oil Trading Room Bundle (includes Weekly Newsletter, Trading Room, Charting and real-time Trading Alerts on Twitter and private Discord Chat Room Server).

Commercial / Institutional Multi User License (for professional trading groups).

One-on-One Trade Coaching (Via Skype or in person).

05
Aug 2019

Oil Machine Trade Software Development Update – v4 vs v3. 

Machine Trading, Office Memorandum , , , Curt Melonopoly

RE: Oil Machine Trade Software Development Update – v4 vs v3.

Today we reverted back to the version 3 software and have abandoned the version 4 software.

The architecture for the version 4 software has too much downside risk (it is too unpredictable in varied market action), even with the possibility of ongoing tweaks (updates). There is no guarantee that we would achieve a state of operation that minimizes downside risk to an appropriate level.

As such we will only be running version 3 going forward and discontinuing version 4 development at least until we can somehow find a way of improving our subscription management software.

Version 3 provided low downside risk with about 83% ROI in real-world testing lasting just over a month (longer duration trading will determine the exact return). In the first month of testing with v3 there was only one day with draw down and it was about -0.2%.

Version 3 also provides for low risk even in unpredictable markets because its architecture does not allow for accumulation type trade positions within a range (it does not accumulate or hold positions), which version 4 did. Version 3 hits key support and resistance with appropriate size and trails out quickly. It is a precision trade architecture design. The version 4 architecture is more designed for positioning within a range, with order flow of entities it identifies as dominant. The two versions are considerably different structurally.

Version 3 will lose sometimes, but will lose very small at all times because it is not an accumulation architecture. This was proven out in real world testing. We estimate that on average over a number of days that about 1 in 10 trading days v3 will see a draw down on average equal to or less than its average day gains.

In early testing version 1 software ran at about 20% ROI, version 2 at 40% and version 3 at just over 80%. All approximate and all short term testing lasting less than 60 days. The v4 software may have reached the ROI goal of 160%, but the road to that goal is too volatile.

Here forward version 3 of the crude oil machine trade software will run and follow-up updates will provide additional information about the architecture of the decisions the v3 software makes to trade so successfully so that our clients that trade manually can use some of the rule-set for their own trading.

And lastly, to the questions I have received about future considerations for v4, the answer is no. At this juncture we would rather enjoy the fruits of our labor as it has been a near 3 year development process (an expensive one) and at some point we must settle in with what we have, what we know works, and what provides the lowest down-side risk.

V3 at approximately 80% ROI per year is world class software and world class is better than good enough.

Again, thanks for being a part of the journey.

Any questions email us [email protected].

Curt

Company News:

SOVORON™ Selects Compound Trading Group Machine Learning Data | Media Release

Subscribe to Learn and Profit:

Click Here for Subscription Service Price Tables.

Free Mailing List(s):

Join Email List for Free Trade Charting Trade Set-ups, Deals, Podcasts and Public Webinars.

Free Swing Trading Periodical Contact Form (Complimentary Swing Trade Set-Ups to Email)

Public Chat:

Visit our Free Public Chat Room on Discord.

Article Topics: crude oil, machine, trading, software, memorandum

 

13
Jun 2019

Crude Oil Machine Trade Software Complete | Rule-Set Strategies, Alerts, Accounts Traded, What’s Next?

Crude Oil Day Trading, Crude Oil Trade Signals, Crude Oil Trading Alerts, Crude Oil Trading Algorithm (EPIC), General Complimentary Newsletters, Machine Trading, Office Memorandum , , , , , , , , , , , Curt Melonopoly

The Crude Oil Machine Trading Software Is Complete.

The information below (in advance of the official white paper) provides a summary of the development process to date, the rule-set (strategies) the code executes oil trades to, what the oil trade alerts will look like on your feed, returns expected on accounts traded and what we have planned in future.

June 13, 2019

As noted above, we have now completed the main structure of the coding for our crude oil trading.

We have previously messaged that we were either close or right at being complete only to find ourselves back down another rabbit hole. This time is actually different, we are done the primary architecture coding, we only have updates (tweaks) remaining. We expect the bulk of that to last at most ninety days.

The software includes eighteen structured algorithmic models (representing time frames from 1 minute charting to weekly), specific high probable trade set-ups, trade sequences within set-ups, order flow analysis, trend (channel) structures on each time-frame and range structures on each time-frame.

The trends (channels) and range trade structures are given the most weight within the decision process of the rule-set. The larger the structure (time-frame) the more weight for sizing and stop loss range. The models, set-ups. sequences and order flow have much less weight in the code.

This (the weights) described above will manifest in trade activity in such a way that trade will become more active and in greater size with the larger the structure. For example, the trending channel from late December 2018 to recent would be a considerable structure within the code and as such the code would size in to that channel at the support and resistance widths of range.

The white paper that we will publish soon will detail the rule-set in such a way that our clients will be able to follow along with the machine trade and understand the protocol that it is executing. This is the first stage for the architecture needed for our trader digital dash board we intend to develop soon.

As the days and weeks go on the software will fire more regularly and will begin to size considerably more than right now because it is coded to weigh decisions within trade trends, structures etc. As the trade set-ups develop the code will fire on them. Obviously the largest structures will be at the end of this start up process. The last few days it has been firing on 1 min, 5, 15 and 30 minute structures.

At first we expect the returns to be approximately .5% per day (if averaged over 30 trading days) increasing to well over 1% per day at most 90 trading days in to the launch. We have tested the code in advance and are confident with this. Depending on our success with “tweaks” the returns could escalate to near 3% per day, we are however more conservative and expect 1%-1.5%.

We are significantly more confident with this version of code simply because we have been down the rabbit hole on every time frame, in every structure, every set up, every order flow sequence on all time cycles competing with the best machines in the world.

We have been there, we went to battle in every arena, we know where we can win and where we cannot. The final version of code will only fire in arenas that we expect 80% + win rate. The larger the structure the larger the return as the software fires through the sequence with the structure.

We tested code on every time frame, in every algorithmic model, every order flow structure and so on and so on. We left no stone unturned.

There are areas of trade in the oil markets (smallest time frames) that are so competitive it would dazzle your mind. The AI’s that are firing in the smallest of time frames are doing so in a way that no trader can imagine. Every time we completed a sequence of trade in the most competitive areas (time-frames) we were schooled in the most advanced AI machine trade the world has to offer. It is manifested in a way no trader would ever expect. Here’s a hint, imagine getting beat every time, in a new way every time and every new way you got beat was a structured, logical, mathematically sound way and the ways seem endless.

Our final crude oil trade code is well outside those areas of competition.

The alerts on the Twitter client feed, in the oil trading room and on the private Discord server will continue to have “M” in the alert if it is a machine driven trade and if I (Curt) am trading I will also identify the alert detail as such. As the days go on the protocol (trade set up) detail will get more and more detailed so that our clients can follow along with clarity.

See also:

Press: SOVORON™ Selects Compound Trading Group Machine Learning Data | Media Release

What’s next?

The next ninety days is for tweaking the code – refining the execution of sequences within structures of trade.

Then near term we will be looking at the trader’s digital platform and API’s etc and then….

AND THEN…. YES, WE HAVE DECIDED to BUILD SOFTWARE FOR BITCOIN MACHINE TRADE. 

This will obviously lead our developers in to other crypto-currencies also.

Any questions send me an email [email protected].

Thanks

Curt

Oil Trading Academy:

If you would like to learn more about how to trade oil, click here and visit our Crude Oil Trading Academy page for complimentary oil trading knowledge – posts from our top crude oil traders that includes learning systems, blog posts and videos.

Welcome to NYMEX WTI Light Sweet Crude Oil Futures.

Subscribe to Oil Trading Platform:

Standalone Oil Algorithm Newsletter (Member Charting Updates Distributed Weekly).

Real-Time Oil Trading Alerts (Oil Trade Alerts via Private Twitter Feed and Discord Private Chat Room).

Oil Trading Room / Algorithm Newsletter / Alert Bundle (Weekly Newsletter, Trading Broadcast Room, Chat Room, Real-Time Trade Alerts).

Commercial / Institutional Multi User License (for professional trading groups).

One-on-One Trade Coaching (Via Skype or in person).

Click here to find all information and pricing on Oil Newsletter, Trading Chat Room, Oil Alerts and more.

Curtis Melonopoly (@curtmelonopoly) is rated Top 250 Stock exchanges authority, covering also Mathematical finance and Economy of the United States

Article Topics: AI, machine trading, trade, software, crude, oil, BTC, Bitcoin, Oil Trading Room, Oil Trade Alerts, Strategy

Follow:

22
Feb 2019

Machine Learning Trade Software Advisory | Crude Oil: (1) Frequency (2) IDENT Program

Crude Oil Day Trading, Crude Oil Trading Algorithm (EPIC), Machine Trading, News, Press Releases , , , , , Curt Melonopoly

February 22, 2019

RE: EPIC Crude Oil Algorithm Machine Trading Software Advisory Specific to Trade Frequency Protocol “Throttle” and IDENT Program Description.

We are now near two months of running the machine trading software for crude oil futures contracts (CL).

During the testing phase, which will continue for some time as we adjust code instructions, the execution of trades by the program is “throttled”. Meaning specifically that the frequency of trade was specifically limited to the highest and then was adjusted to a higher win probability threshold.

The result of the initial testing achieved near 100% win side trade accuracy, but less than optimum trade frequency. Increased frequency may (will in our estimation) return a higher ROI – assuming the win rate percentage achieved is high enough. This of course is a complicated calculation within the code that reflects the win side average per trade return vs. loss side average per trade. In short, the loss side is programmed to be less (limited by way of higher frequency executions – tight stop triggers) and when trade is on win side the trade profit is increased via trade size that is progressively trimmed as the trade is in progress. Refer to private Discord oil trade chat server for real-time discussion between developers and traders for more detail.

An article is available at this link that displays some of (actionable by a human trader executing trades manually) the oil machine trading results, much of which was throttled considerably and much of which had human intervention – in other words, had the software been released to execute totally autonomous the returns would have been considerably higher – but we are testing. The highlighted trades returned a 63% increase on the “large account” test for the one month duration. This achievement was specifically to the alerted trades, not the higher frequency machine trades.

The “alerted trades” meaning that which could be considered actionable alerts to our subscribers. The machine software executed many times more trades but our current alert system platform (Twitter private member feed, Discord private chat server, Oil trading room live broadcast) cannot for the most part distribute alerts fast enough for the higher frequency trades to be considered actionable by a human executing trades manually (a trader digital platform is on the team WIP to remedy this). In consideration also is that the higher frequency trade protocols could easily be reverse engineered to expose the proprietary protocols under our IDENT program – this remains a discussion point internally and how the higher frequency trades will be shared is in question (more on that at a later date).

The “throttle” was initially set to approximately 20 x and over the course of fifty days progressively lowered to function near 10 x with less and less human intervention along the way. 20 x for example would result in twenty times less trade frequency than would otherwise be if the software was not “throttled” at all.

Today (Feb 22 at 2:11 AM EST) the code was adjusted considerably to be “throttled” to be less than 10x and will be lowered progressively over the next 7 trade days. The win rate vs. return as it would be calculated over a month is the achievement bar (goal) in focus. More on this objective and other clarification in near future updates.

Market condition will also result in variance of execution frequency as will holiday weeks specific to the model(s) divergence.

The main takeaway: In to next week the frequency of trade will be considerably higher with an objective being to find the most optimum throttle setting to achieve the highest return. The win rate is expected to near 80% and not near 100% and the return on equity on a monthly basis to increase considerably.

The 63% monthly return (monthly return in this instance meaning account equity size increase as it relates to alerted trades only) is a favorable start, however, our team believes 100% + return per month is consistently attainable (on average over a year) and in a perfect machine executed world 300 – 500% being optimally possible. For now our objectives are to achieve consistent wins at higher than 80% with a frequency of about 60 to 120 trades per month with a return averaging 100% per month (the bar).

The IDENT program is a protocol specifically to order flow identification of market participants achieved by way of historical pattern recognition of between 20 – 40 entities that we consider largest and approximately 200 entities that we consider important enough to attempt to track. The entities are prioritized in what we describe as an “alpha” order. The IDENT program is in large part the topic of this recent article at this link that describes the influence of machine trade in the crude oil trade market as experienced by our lead trader and is in large part the reason for the “intuitive like” nature of our software protocol.

The IDENT program seeks to enter trade direction with prioritized alpha order flow and exit in the same fashion. It is a proprietary process and the instruction set within the code architecture will in large part remain private.

For more information on how our development has progressed, refer to this link that will immerse you in a series of articles written from first hand perspective of the day to day trading of our lead trader with crude oil futures.

Thank you.

 

 

 

 

 

 

19
Feb 2019

“The Bullet Hits Before You Hear It” | Why You Can’t Beat Machine Trading Algorithms.

Crude Oil Trading Strategy, General Complimentary Newsletters, Lead Trader Blog Post, Machine Trading , , , , , , Curt Melonopoly

I Have Been Down the Rabbit Hole. 

I know my journey (of the last two and a half years) few have traveled. I know this to be so, like I know I breathe.

I didn’t know before I went down that hole, but I know now – how much I did not know before I went down that hole. And it’s huge. I knew nothing. Few know anything.

I can’t imagine many other disciplines in the world as off-side as this. Nothing, and I mean nothing in regular market banter, conventional stock exchange media or social media ever deals with the reality of what is down that hole. They don’t even know there is a hole (most).

Why is this topic of any importance to a trader or investor?

The topic? A human trader cannot beat real machine learning software and that will matter before the humans know it mattered.

A human trader cannot beat real machine learning software and

that will matter before the humans know it mattered.

Assuming the 80/20 rule applies to the markets, then 20 percent win 80 percent of the trades and reap 80% of the reward (ROE). I don’t know what the real numbers are – it was likely closer to 90/10 before machine learning entered the public stock markets. I would venture to guess it’s 97/3 or so now. But I don’t know.

The problem looks like this… what happens when the machines (run by less than .001% – a guess) garner 90% or more of the market return? Is that possible? I know it is, I know it may be true now, and if not it isn’t far away. What percentage of current liquidity is machine learning trade driven? What percentage of that is on the win side?

What does that look like in the future? How far away is that future? I will bet that future is here now and it has enormous effect on your earning potential (as a human trader). And I will put forward right here that it will end the way humans trade in global markets about five years out. It already has, the humans just haven’t accepted reality.

So why then is this so important? We’re here to win. We trade to win. To earn. To see return on equity. Return on time. The path forward is critical for any trader that derives their income from trading.

Early adopters will win. They will win because they will develop relationships with firms that will provide solutions. They will win because they will adopt the technology, relationships, financial rewards before the technology is out of reach (financially speaking). Or perhaps, never available at certain levels of society. Never available is more likely.

Early adopters will win.

The market is already littered with technology built on poor science. It simply doesn’t work. But the firms that have figured it out… have really figured it out. How long does it take them to hit market capacity? Will they share the technology? I say no, they won’t be sharing.

There are many questions.

At minimum, it’s prudent in my view for a trader to cozy up to the developers. This isn’t a sales pitch, we’re beyond selling anyone. We’ve completed our first machine learning software – we don’t need to sell you. So why write this article? Because I want to share something I’ve learned in the process of development that I think is of critical importance to anyone that has followed our journey. I feel a responsibility to share. Share what  you ask?

You can’t beat the machines. It’s not possible. And I know. I’m a damn good trader and I can’t even beat our first generation software with crude oil futures trade. I don’t think it has lost a trade this month (maybe it has but I don’t think so) and we’re near three weeks in to the month. And it’s not that it hasn’t lost, it is more about how it wins.

It knows before I do. It enters before I do. It trims in to positions and exits when I wouldn’t. It knows things I can’t know, I can’t see. It sees every line on every book in the library instantly, while I search for the right book on the shelf.

It sees every line on every book in the library instantly,

while I search for the right book on the shelf.

How you ask? It has intuitive like capabilities (as I do) but it can process the decisions (as if intuitively) many times faster than I. It has systematic approaches to trade (as do I) but it can process the decisions on thirteen time-frames considering the historical structure of the financial instrument and how each time-frame relates to the next and which structure or time-frame should trump various trade execution decisions (the rule-set).

It is simply faster. It can process 8000 rules and how each rule relates to the next in each of the structures on each time-frame instantaneously. That instantaneous decision would take me at least 12 months full time of charting, historical back testing and deep thought to conclude that one decision. The machine executed on the decision and left the trade behind before I glanced over and seen it was over. I didn’t have time to acknowledge it was leaving the scene.

It’s not only faster, but precise. It enters and exits with absolute precision.

Yesterday (President’s Day holiday) it executed on one trade. The biggest move of the day on a slow day and it executed before the move happened. It shorted oil, I sat watching thinking why the heck is it short here? Tick tock tick tock boom, oil dropped about 37 points near instant, on a low range boring holiday trading day. And it covered in a flash before I could process why exiting the trade at that juncture of trade on the chart was valid. It is fast and it acts as if it is intuitive. And it is only first generation software.

Here’s a post that shows the trade;

A trade or two prior to yesterday’s was the same way. I couldn’t believe what I was watching.

Here’s another example, it knows over and over again where the real move in a time frame is before the move.

And an example of how precise it is in comparison to my personal trade executions;

It’s first month (January) it rang up 63% in oil trade account gains and it was yoked to a human at all times that throttled its executions by about 10 to 1. What am I saying? It could have traded up to 10x the return (assuming the same win rate and ROE on each trade would have transpired had it been non-yolked).

It’s first month (January) it rang up 63% in account gains.

Over the last few days we’ve allowed it autonomy – to a point. It can execute with autonomy when it is executing but we still have it throttled to about 5 to 1, this will be slowly adjusted / released. This week is a holiday week so there is issue in the structure of the models so it will be a slower than usual machine trading week for our model, but next week will be a mad house – a slaughter house. I’m not exaggerating. It doesn’t lose. Okay, it does – maybe, but rarely and for next to nothing for loss when and if it does. If it’s wrong… its out and fast.

If you think this is exaggeration, visit our public facing Discord trading chat room (click here) and randomly ask anyone to step forward and tell you I’m wrong (members I am referring to). Or check out the alert feed yourself. I win around 90% of my personally executed trades in oil (yes documented), it (the machine learning software) wins something nearing 100%. But its wins are the real meat of each trade. My trades are choppy. It harvests the move in a way I cannot. The compound return effect on the difference is astronomical. Click here for a recent article I posted about compound trading gains in oil trade.

We have been working day and night for over two years to develop machine trading software that really works. Why do I say “that really works?” Because most is garbage. Below are the reasons why most algorithmic trading is a waste (how ours was developed) and why you the human trader cannot beat real machine trading execution in the stock market.

Take four people (average at any given time in the development process), have them work 60 – 80 hours a week for 2.5 years. That’s about 14,000 hours. If the methodology used is right you then have at least another 14,000 hours to refine the software rule-set along with constant updates etc. We have now completed the first 14,000 hours. What has that experience taught me? Primarily that a human trader will never beat machine software. And that doesn’t consider machine software that becomes intuitive like – AI, Artificial Intelligence.

Here are just a few (and I mean a few) reasons why you will never out trade the machine – specific to the methodology of development we used to develop our first machine trading software for crude oil futures contracts CL. Yes, I am going to tell you how we did it. Why? Because I won’t tell you how our intuitive development is implemented, that is proprietary and always will be. Here’s the nuts and bolts:

  1. ROI – First month the machine garnered a 63% increase in trade account size and that was only the actionable oil trade alerts. Not the machine HFT returns. This means the software executed many more trades than what was alerted. We can only alert what a human can type fast enough to alert that could be actionable for our membership. Next on our list is a real-time feed for our members (automated alerts). In other words, the machine gained much more than 63% on its trading account, but that is private and always will be. What is public is what we alert that is actionable by a human trader executing trades manually. We are judged on what data can deliver as actionable to our clients.
  2. INSTANT EXECUTION OF DEEP TECHNICAL KNOWLEDGE – Take thirteen time-frames of crude oil (the charts) and find the structure of the financial instrument on each time frame (this is not systematic machine trading, this is an intuitive like process). Not to mention the time involved and cost. The human can’t process decisions on thirteen time-frames (both systematic and intuitive like and as they relate to each other, as described earlier in this article).
  3. INTUITIVE EXECUTION, INSTANT – Each time frame structure as it relates to each other. Continuing specifically the intuitive like component of point 2 above… imagine constructing the models for the structure of the financial trading instrument on thirteen time frames, that in of itself is a massive undertaking. Then being able to almost intuitively determine how intra-day trade relates to each and which trumps the other. This is massive.
  4. FAST EXECUTION. The machine can out execute any human with orders in and out and trailing and on and on. Complex structures of entries and exits and more instantaneously. This is critical for return on each trade.
  5. PRECISE EXECUTION. Have you ever watched crude oil trade on the one minute chart? Precise execution with orders that change frequently in a flash of a second increases returns on each trade considerably. You can’t imagine the importance until you’ve been down the hole.

I am not speaking to;

I’m not speaking to conventional hedge fund robo adviser software. Most of it is junk designed to rob the masses taking advantage of the casino mind or lazy investor.

I’m not speaking to high frequency trading that leverages machine speed, order flow or execution locality. That is a form of HFT we have no interest in. We want transferable knowledge as it applies to the natural trading structure of the financial markets. Transferable in that the process used to derive the model for one can be applied to another.

I’m not speaking to run of the mill python code some random developed in his/her basement with 500.00 and an idea of how an instrument trades (the systematic process).

And finally, I am not speaking to the news oriented bots running software trades on intra-day media or geopolitical driven events.

The intuitive like component is artificial intelligence – machine deep structured learning.

The intuitive like component, beyond systematic machine trading is where the magic is, this is where the depth is, where the future is and the success of such an initiative lies. The intuitive like component is artificial intelligence – machine deep structured learning. It is (as it applies to where we are now) the early building blocks of autonomous machine learning trade.

Beyond systematic machine trading is where the magic is, this is where the depth is, where the future is and the success of such an initiative lies.

How did we get intuitive like software to work? What does intuitive like mean to us?

Here’s a glimpse… a real trader with decades of experience traded real-time for hundreds of hours live with software developers that extracted the intuitive like human understanding – real-time, asking questions, engaging in the why and how at each tick in the chart.

We lived together inside the trade, inside the natural trading structure of the financial instrument (crude oil) and then we replicated its nature in to the code. Only now… we have manifold times more horse-power.

We lived together inside the trade, inside the natural trading structure of the financial instrument (crude oil) and then we replicated its nature in to the code.

The new brain – the new trader, the intuitive like software… can execute hundreds of times faster on thousands of times the information second by second. Every tick on the chart is a complete new set of rules that need confronting, they need to be examined from every angle, back tested, related to each time frame, a plan derived and a trade has to executed right now. A series of right now. With precision.

The bullet hits before you hear it.

This is why the human will never beat (real) machine learning trade software. The only question that determines how good the software is, is how good the trader was that the developers used to extract from that created the entity (the software) and what process was used to do that. The cost? 14,000 – 28,000 hours at hundreds of dollars per hour – for a generation one package. And that is just the start.

It is a different world and we’re not by far the first out of the gate. But I know we’re running one of the better models out there. That I do know. Because it wins when it goes in to battle.

Any trader worth their salt will soon, if not already, understand they need a plan to engage this new frontier.

I also know that any trader worth their salt will soon, if not already, understand they need a plan to engage this new frontier. If you don’t you will regret not taking the time to forge your future. Now.

Best and peace,

Curt

Learn How to Day Trade Crude Oil Here:

Crude Oil Trading Academy : Learn to Trade Oil – real life articles / examples from an expert crude oil day trader.

Read Our Press Release About The SOVORON™ agreement (click here):

About SOVORON™

SOVORON™ offers a unique trading service providing clients with technology application based Machine Trade of personal investment accounts. To explore their unique client service structure click here http://sovoron.com/ or call 1-849-861-0697.

About Compound Trading Group.

Compound Trading Group is a market data provider to retail, commercial enterprise and institutional traders.

Trader Services – Compound Trading Group provides trader data services such as algorithm development, periodicals, trade coaching, trade alerts and live trading rooms. The near term objective is a digital dashboard environment for traders to fully engage machine trade and intelligent assisted trade data offered only at the commercial enterprise level.

Commercial Enterprise Services – Compound Trading Group develops financial instrument algorithm models and provides connect-ability to its proprietary AI Machine Trading software / data (representing various financial instruments) to private trade and institutional firms. Compound Trading Group also provides enterprise trader training, integration services, custom software / data constructs and strategic partner development opportunities.

Learn more at https://compoundtrading.com.