Build Alpha Trading Software creates, tests and codes trading strategies with the click of a button. Demos: buildalpha.com/demo
Boca Raton, FL
- Tweets 3,077
- Following 0
- Followers 7,796
- Likes 754
The Commitment of Traders (COT) report tells you who is positioned where in futures markets
and
is one of the most powerful (and overlooked) ways to add environment and context to your trading strategies.
Let's go over what it is and 7 useful signals you can test today...
The report tracks three market segments and how many contracts each segment is long or short in each instrument:
→Commercials (hedgers)
→Non-Commercials (large speculators)
→Non-reportables (retail / small traders)
The report reflects positioning as of Tuesday, but isn't reported and tradeable until Friday.
The report can tell you: "wow, commercials are net long SP500 and retail is leaning short" which tells you something different than "wow, retail has never been more bullish SP500".
Would knowing the above change how you trade? It should...
Build Alpha includes normalized COT positioning + COT Index data. Here's some clever ideas to test:
• Hedgers − Retail spread > X
• Hedgers bullish + retail bearish (or opposite)
• Hedgers vs non-commercials divergence
• Commercial net positioning accelerating
• Hedger/retail spread widening
• Commercials reversing from an extreme
• Hedgers + retail unusually aligned
I made a drop-in COT custom indicator file you can get at the link below with these ideas and more to test alongside the built-in COT signals.
COT helps answer:
· Who agrees with me right now?
· How extreme is the positioning?
· How has this positioning affected price?
Does it make sense to take upside breakouts when the biggest players are net short? Does dumb money agree with my position? Who is likely to be on the other side of this trade?
If you haven't asked your trading strategies these questions maybe it is worth a look.
Now you can do it easily. With no code.
2
3
41
3,518
Full write up with signal file: buildalpha.com/commitment-of…
4
291
Have a trading idea you've never properly tested?
This video shows full path from signal → simulation → export to your platform.
· prompt signal in English
· select for use in simulation/generation
· export code (NT8 shown in video)
· show matching results
No coding. Now you can automate your ideas and see the data behind them. More coming..
3
7
41
2,229
Sometimes the easiest way to find an intraday edge is to start with daily data.
Daily data is less noisy, making broader signals easier to identify.
But what if most of a daily strategy’s profits come from just a few hours? Do you check?
Build Alpha’s Intraday Edge feature searches shorter trading windows within your daily strategies to see whether you can capture much of the original edge with much less time in the market.
Think of it as finding intraday strategies backwards. Now with one-click.
1
5
38
2,791
Full write up with strategy example buildalpha.com/intraday-edge
4
341
One I forgot in this list is swing highs/lows.
Quantify these by highs that are above the N bars to their left and to their right.
or more simply:
High[N] >= highest(high, 2N * 1)
I put these inside the EventPrice function which returns a value whenever an event is true. The return value is High[N] which is the swing high, e.g.
Then you can buy nice breakout spots
What if your entry signal is fine but you’re entering at the wrong price?
One finding from my early LLM orchestration + Build Alpha experiments has been changing the entry order type and price level often delivers more bang for your buck than having the LLM author another entry signal.
The same entry signal can behave very differently when you:
• Enter immediately
• Wait for a breakout with a stop order
• Wait for a pullback with a limit order
10 entry ideas worth adding to your library:
1. Daily open ± k × ATR
2. VWAP ± k × ATR
3. Opening range high/low
4. Previous day’s high/low
5. Overnight high/low
6. N-bar high/low (Donchian)
7. Signal-bar retracement
8. Partial gap fill
9. Moving average ± k × ATR
10. Compression-range breakout
What are some entry types in your library?
1
2
33
3,100
What if your entry signal is fine but you’re entering at the wrong price?
One finding from my early LLM orchestration + Build Alpha experiments has been changing the entry order type and price level often delivers more bang for your buck than having the LLM author another entry signal.
The same entry signal can behave very differently when you:
• Enter immediately
• Wait for a breakout with a stop order
• Wait for a pullback with a limit order
10 entry ideas worth adding to your library:
1. Daily open ± k × ATR
2. VWAP ± k × ATR
3. Opening range high/low
4. Previous day’s high/low
5. Overnight high/low
6. N-bar high/low (Donchian)
7. Signal-bar retracement
8. Partial gap fill
9. Moving average ± k × ATR
10. Compression-range breakout
What are some entry types in your library?
2
6
48
5,238
How can you tell if your exits are overfit?
System traders can overfit both entries and exits. Hard to tell which but we need to check both.
Monte Carlo only changes the order of existing trades. It preserves the profits and losses produced by the exact exit settings from the backtest.
Build Alpha’s Randomized Monte Carlo Test challenges the settings themselves:
• Keep the entries fixed
• Randomly vary exit parameters on each trade
• Repeat 1,000+ times to get a distribution
For example, a strategy using a 2 ATR stop and rolling 5-bar low as exits might change the ATR multiplier and rolling window for each trade.
No exit rules are added or removed. Just modified.
If most paths remain profitable, stronger confidence you didn't overfit the exits.
If profitability collapses, you're likely in for a rude awakening when you go live. At least you caught it first.
Your equity curve is one possibility. It shows what worked with one configuration. This test reveals how much depends on getting that configuration exactly right.
Stress test both your entries and your exits.
6
10
119
6,874
nitter.net/jordanfogel/status/189…
CEO of Renaissance Technologies, Jim Simons, walked down to the Federal Reserve Bank and copied interest rate history on paper by hand.
Alternative Data → Question it helps answer
· VIX Term Structure → Is the market pricing fear or complacency?
· Interest Rate Curve → Is liquidity expanding or contracting?
· Economic Releases → Is today’s price action driven by macro events?
· AAII Sentiment → Are retail investors excessively bullish or bearish?
· Dark Pool Index → What are institutions doing beneath the surface?
· Gamma Exposure (GEX) → Are options dealers likely to dampen or amplify volatility?
· Market Breadth → Is the move supported by the broader market, or just a few stocks?
· Weather → Could weather materially impact supply, demand, or seasonal behavior?
· Google Trends → Is public attention accelerating before price reacts?
· Commitment of Traders Report → How are traders positioned?
Alternative data gives price action much needed context.
Better trading systems start with better questions. Take it from the G.O.A.T🐐
Jordan F
7
33
2,893
If you only build strategies on the one version of price history the market gives, then you're missing out on new ideas and robustness.
Some of the most impressive results in the field of AI have come from generating additional synthetic data 🫣
1. AlphaGo Zero and DeepMind
Earlier AlphaGo versions learned from human games. AlphaGo Zero learned through self-play, generating its own training data.
After three days, it defeated the version that beat Lee Sedol (human expert) by 100 games to zero.
2. Microsoft’s phi-1
Microsoft combined selected web data with AI-generated coding textbooks and exercises.
After additional training on synthetic exercises, its small coding model improved from roughly 29% to 50.6% on the HumanEval benchmark.
3. Deep Hedging: JPMorgan and ETH Zurich researchers
Researchers trained hedging strategies in simulated markets, incorporating transaction costs.
Their approach outperformed a standard frictionless-model hedging benchmark in those simulations.
**for traders, synthetic data is compelling**
Would your strategy still work if prices moved slightly differently? If volatility changed? If winning and losing trades arrived in a less favorable sequence?
Build Alpha’s Noise Test, Vs Shifted, and Monte Carlo permutation tools help answer these questions through synthetic price variations and alternative trade sequences.
Create thousands of synthetic price series, keep elements that make markets markets, and re-trade your strategy across them.
Instead of overfitting the known history, you can build something that withstands 1000s of possible disturbances. Confidence 📈
2
28
2,631
Build Alpha retweeted
If you're thinking about automating or still placing some trades manually to "hedge" your automated systems,
do this little experiment my mentor had me do.
Mark every manual trade in a spreadsheet for 3 months or a quarter. Do not cheat. Mark every single one.
1/
1
1
6
1,407
Build Alpha retweeted
Nice YT channel @buildalpha !
1
1
2
476
One of the biggest fatal flaws I come across is what I call "strategy hopping". So many traders make this mistake and don't even realize it.
Flip a fair coin 10 times. You might get 3 heads. Or 5. Or 6. Or 9.
No way to tell if the coin is rigged in 10 flips. A fair coin and a rigged coin produce the same range of outcomes at this sample size (number of trials).
Flip it 1,000 times and you will know if it's a rigged coin or not.
In statistics, this is known as the Law of Large Numbers. The truth only arrives once you have enough observations, and before that point you are seeing noise and mistaking it for information.
Now consider a trader who watches a few trades and decides it is broken or tweaks his strategy or finds a new strategy altogether...
This is "strategy hopping" and is an account killer.
Each change or tweak restarts the counter.
Back to the left-side of the graph you go.
The trader can be trading for four years and never leave the left-side of this graph. He's stuck in randomness and he cannot escape via strategy hopping. Strategy hopping is actually why he's stuck and bleeding.
Please do the work up front before risking capital. Validate properly, size so you can survive the bad stretch, understand the system's expectancy and where you can be in the next N trades and then stick to it.
You must let the Law of Large Numbers play out. This is the only way to escape randomness and capture the edge you've found. It took me way too long to learn this.
4
3
26
2,587
For those that need to see it today - you can set rules to trade on or avoid news event days buildalpha.com/news-event-tr…
3
2
819
I used AI to build 1000 trading strategies for $0.04
piped.video/T0rjdGpcqxQ?si=N5kf…
Building a backtesting engine that never stops searching. 24/7.
The next generation of Backtesting - AutoTune update:
Automated Strategy Discovery
→ Set initial symbol(s), date range, signal universe
→ Connect any LLM via API key
→ Starts generating new strategy ideas
→ AI monitors performance for plateaus
→ AI changes settings, creates new rules, restarts
→ Profitable ideas advanced to automated validation
→ Unprofitable or failing stress tests automatically rejected
→ Export code to any major platform (NT8, MT5, TradingView, Python)
→ Memory is updated locally so next search doesn't start from scratch
Some strategies work.
Most don't.
But now we find out at computer speed.
Instead of manually hunting for the next edge, there is now a system that can search → test → reject → discover → repeat… 24/7.
Still building. Still improving.
But this has been one of the most exciting updates in a while.
1
4
25
3,659
A Stanford professor turned $100k into $7M through rebalancing two stocks daily. It’s called volatility harvesting.
No predictions. No ai. Just math.
I wrote about this a few months ago.
Les Hicks
5
33
277
53,902