Formula δ1

2.2K posts

Formula δ1 banner
Formula δ1

Formula δ1

@FormulaDeltaOne

QR, HFT

Se unió Temmuz 2011
203 Siguiendo10.6K Seguidores
Tweet fijado
Formula δ1
Formula δ1@FormulaDeltaOne·
AMA - Shill me your HFT/algo strategy idea and I’ll tell you why it won’t work.
English
65
5
178
97.2K
Formula δ1
Formula δ1@FormulaDeltaOne·
@0xLoris Haha, fair point. I’ve been so busy lately!
English
0
0
0
177
Formula δ1
Formula δ1@FormulaDeltaOne·
A lot of people suddenly followed me today. At first I didn’t know why, because I wasn’t tagged in anything etc. Then I stumbled upon this post/list. TY for the reminder, I should post some actionable edges again. 🤣 If I get over 10k, I might do some 🧵s again.
cephalopod@macrocephalopod

I also have a list of people who are genuinely worth following who sometimes reveal actionable edges, obviously it’s a lot shorter x.com/i/lists/184326…

English
2
0
54
14.7K
Nunchi
Nunchi@nunchi·
Agentic Trading Competition is coming. @karpathy proved an AI can run experiments autonomously and find what humans miss. We ran the same loop on live trading strategies: 251 experiments, no human intervention, Sharpe 2.7 → 21.4. Now we want to see what you can build with it.
English
60
37
394
213.5K
Formula δ1
Formula δ1@FormulaDeltaOne·
What’s the AI version of putting laser eyes on your profile pic?
English
1
0
2
821
qm
qm@quantymacro·
@GryptoGoon alpha decay is when you lose money. regime change is when I lose money
English
7
6
164
5.9K
Goon
Goon@GryptoGoon·
Had an interview with a grad and he said he built a regime change detection model. I asked him if it predicted the US and Israel going into Iran. He didn’t get the joke. Instant no hire. Also. What the fuck is a regime change in regards to trading. Am I retarded?
English
29
3
325
38.9K
Formula δ1
Formula δ1@FormulaDeltaOne·
RIP Voidmage Prodigy
HT
0
0
1
1.7K
wishful_cynic
wishful_cynic@EvgenyGaevoy·
@macrocephalopod i was joking btw, just felt appropriate to prompt chatgpt to write a reply to this particular post😅
English
3
0
11
614
cephalopod
cephalopod@macrocephalopod·
Completely agree, and in addition, it’s incredibly rude and disrespectful of your followers to post AI-generated text on your twitter account. If you can’t take the time to think your own thoughts and put them into words, why should we bother reading them?
Daniel Litt@littmath

IMO it should be considered quite rude in most contexts to post or send someone a wall of 100% AI-generated text. “Here, read this thing I didn’t care enough about to express myself.”

English
12
7
282
31.7K
cephalopod
cephalopod@macrocephalopod·
Been working on something in my spare time over the past few years. No automation, completely discretionary. This is entirely outside of my day job. It's been a lot of work, but I'm quite proud of these consistent results.
cephalopod tweet media
English
36
2
334
63K
sysls
sysls@systematicls·
There is such a persistent career advantage in being obsessed with your work. I don't mean "I love my job" and you get in by 9 and leave by 5. I mean the quintessential zuckerberg-esque "I'm working all the time because I never stop thinking about facebook (meta)" kind of obsession. One super advantage comes from keeping your work in ram all the time: it drastically increases the probability that you come up with an innovative/useful idea throughout the day AND you lose almost no time "getting warm" when you do have space to work.
English
13
17
351
21.8K
ltrd
ltrd@ltrd_·
What I love about HFT and market microstructure is that you have so much data and noise that almost nobody wants to go deep down into it and find something important. I am not even talking about the real alpha on the market, but here, on X, there are not a lot of people that have ever shown anything valuable (I do not talk about revealing alpha, just make a good stuff) in their posts regarding this timeframe. PS: The edge is here.
English
10
12
315
26.1K
Formula δ1
Formula δ1@FormulaDeltaOne·
@macrocephalopod The trouble with responses like these is they just give more exposure/reach to the slop.
English
1
0
18
2.7K
cephalopod
cephalopod@macrocephalopod·
My favourite conformal prediction crank is becoming a “computer vision for trading stocks” crank. Great to see the glow up 🥰 Hopefully doesn’t need saying for my very smart followers, but this is pointless trash that no serious prop firm is even considering, let along using.
Valeriy M., PhD, MBA, CQF@predict_addict

📈 JP Morgan and top quant firms are using computer vision to trade stocks. Why aren’t you? Wall Street isn't just looking at candlesticks anymore — it's scanning time series as images. 🔍 Enter the Gramian Angular Field (GAF): a transformation that turns time series into textures, enabling models like CNNs and Vision Transformers to read financial data like a heatmap. GAF encodes the angular cosine similarity between every pair of time points — revealing hidden patterns, transitions, and temporal structure that lags and moving averages simply can’t. If your signal has: 📊 trend shifts 🔁 cyclic structure 🔥 anomalies or bursts …GAFs turn it into a form machines can see and classify. 🧠 This week, we’re dropping a full chapter on feature engineering — including GAFs, recurrence plots, MTFs, and more. It’s part of the most comprehensive feature engineering treatment in time series ever published: 📦 120+ techniques 📚 18+ structured feature classes 🧪 With full Python code, visuals, and ML integration 🚀 The book price goes up after this chapter drop. 🎯 Grab it now and lock in lifetime access: 👉 valeman.gumroad.com/l/MasteringMod… #TimeSeries #ComputerVision #GAF #QuantFinance #CNN #VisionTransformer #Forecasting #FeatureEngineering #Python #DataScience #MachineLearning #DeepLearning #Finance #JPmorgan #AlgoTrading

English
29
7
345
62.9K
sysls
sysls@systematicls·
I hate it with a burning passion when team members compare themselves to the LOWEST DENOMINATOR. THIS IS A WINNERS TAKE ALL INDUSTRY. It doesn’t matter that you are NOT THE LAST. The only thing that matters to me is that you are NOT FIRST.
English
3
0
27
6K
Formula δ1
Formula δ1@FormulaDeltaOne·
@TheSpeculator0 But that would have awoken the Ents and they would have marched towards Isengard.
English
0
0
1
375
Speculator
Speculator@TheSpeculator0·
Imagine how much GDP we could add by damming this river and using the nearby forest for fuel
Speculator tweet media
English
2
0
16
2.2K
Formula δ1
Formula δ1@FormulaDeltaOne·
@o_wutang Of all the things that didn’t happen, this didn’t happen the most.
English
0
0
5
1.2K
Alia Wu
Alia Wu@o_wutang·
in a mckinsey training at b school a few years ago, we were analyzing the profitability of a vending machine. everyone followed the textbook: foot traffic, location, climate. i said: does it take apple pay? the facilitator blinked, said it was an “interesting” take. the whole room laughed. looking back now, that was the start of the payments digitization wave. it turned out to be the determining factor. just thought of that. groupthink isn’t always the right answer.
English
3
0
30
4.2K
Formula δ1
Formula δ1@FormulaDeltaOne·
@6_Figure_Invest Ok, we have distinct terminology. If your statement boils down to “never send market orders without pre-specified price” than it is trivially correct (for any market, not specifically options) and I would subscribe to it. 🤝
English
1
0
3
145
Vance Harwood
Vance Harwood@6_Figure_Invest·
@FormulaDeltaOne An IOC order with a price *is* a limit order... If no price is specified it means best available which might change from the screen value while your order is being processed.
English
1
0
1
156
Formula δ1
Formula δ1@FormulaDeltaOne·
I don’t understand the “you’re not guranteed to get the b/a you see” point. Obviously if you send pure market orders with no price specified than you can probably buy for infinity and sell for zero, but who does that? I meant that you send an IOC with a specified price.
Vance Harwood@6_Figure_Invest

Market orders trade price certainty for execution certainty, and limit orders do the reverse. Three reasons to not use market orders for options, and two reasons where market orders make sense: 1. With a market order you are not guaranteed to get the bid/ask you see, it can change at any point, and if it does your fill won't match what you expected. 2. Unless the bid/ask spread is very tight you can often do better than the listed spread by putting in a limit order inside the spread. I usually start a the mid-price point between the bid/ask. This works particularly well with combination orders like spreads/butterflies where you are trading multiple options with multiple strikes/expirations/direction (buy or sell). Mid-price fills are common. 3. If you are trading in size, multiple contracts, then you will likely get fills at different prices, always worse than the quoted bid/ask with a market order. When to use market orders? 1. For very liquid securities that have options with very tight spreads. The bid/ask prices are fluid and there is very low risk that your will get a bad fill 2. In fast markets where you want/need the trade to fill immediately. Chasing a market that is moving away from you with limit orders is a bad idea, the risk is much higher than the potential gain. Limit orders for light traded ETF are often a good practice also. sixfigureinvesting.com/2012/01/tradin…

English
4
1
7
4.7K
Formula δ1
Formula δ1@FormulaDeltaOne·
Also, if you “trade in size”, your limit orders are gonna stick out from the order books, so you are guaranteed some slippage.
English
0
0
2
1.4K
Formula δ1
Formula δ1@FormulaDeltaOne·
In that case the only thing that can happen is that someone hits/lifts/cancels the level before (in which case the price is already running away from you, but no “bad” fill) or someone tightens in the opposite direction (in which case you get a better price than your IOC price).
English
1
0
4
1.7K