Instagram story viewer> @falaktb> Posts

Falak Khan

@falaktb

14.4K

followers

93

following

Quant Developer
Founder @lse
🎓 @londonschoolofeconomics

POSTS STORIES REELS TAGGED

Download All

Today, we’re open sourcing the LSE Terminal. A new foundation for quantitative trading. by @falaktb

652

34

2 months ago

Principal component analysis reduces a set of correlated assets down to the few underlying factors that explain most of their movement. In quant finance it exposes how concentrated a portfolio really is, since positions that look separate often trace back to the same factor. It is the first thing to run when you want to see what is truly moving a portfolio.

#PrincipalComponentAnalysis #quant by @falaktb

453

2

2 months ago

Currently building our own LLM and parsing language for traders to query the entire archive straight from memory. #opensource #marketdata #quant by @falaktb

1k

54

3 months ago

Construction going on outside

#h100 #tcn #alternativedata #machinelearning #quantfinance by @falaktb

431

19

4 months ago

Options market makers gamma scalp constantly as part of managing their books. As price moves, their delta exposure changes with every tick, so they rebalance by selling into rises and buying into falls. Those hedge adjustments can create gains that offset the cost of holding the option position.

#gammascalping #options #deltahedging #quantfinance #volatility by @falaktb

3k

35

4 months ago

A Kalman filter maintains an estimate of an unobserved value together with the variance of that estimate, which is the minimum variance solution under Gaussian process and measurement noise. Each step advances the estimate with a model, raises the variance by the process noise, then revises the estimate by the Kalman gain multiplied by the difference between the measurement and the prediction.

#quantfinance #kalmanfilter #timeseries #statisticalmodeling #machinelearning by @falaktb

4k

38

4 months ago

Processing market data in hardware rather than software is the single variable that gives FPGA firms a structural edge at the matching engine. #fpga #hft #quant #optiver by @falaktb

2k

27

5 months ago

Part 2 will cover how we minimise latency through colocation and FPGAs.

#predictionmarkets #polymarket #hft #quant #arbitrage by @falaktb

2k

31

5 months ago

Level 3 order book data records every individual order that hits the matching engine and every change made to it afterward, while Level 1 only ever surfaces executed trades. That gap is the reason quant desks pay for direct exchange feeds at all.

Once you can see where the resting orders actually sit, the next price move becomes a function of book state rather than a guess. Order book imbalance and queue position both belong to Level 3 and have no Level 1 equivalent.

#quantfinance #algotrading #orderflow #hft #wallstreet by @falaktb

2k

55

5 months ago

Pearson correlation measures linear dependence between two return streams as a single number between minus one and plus one. Compute it across thousands of instruments and you get a correlation matrix, the structural map of how the market moves together.

Pairs that share a factor (same currency leg, same sector, same risk regime) cluster near plus or minus one by construction. The residual between them, fit by OLS, is the variance the shared factor cannot explain. If that residual is stationary, it mean reverts.

That is the trade. When the spread deviates beyond two sigma, you sell the side that moved and buy the side that didn’t, then exit at the mean. This is the math behind statistical arbitrage, the strategy that has generated billions in P&L for hedge funds since the 1980s.

#quantfinance #algotrading #pearsoncorrelation #hedgefund #correlation by @falaktb

10k

74

6 months ago

That is why models like this matter. Instead of assuming every feature carries signal all the time, a transformer can shift weight across returns, volatility and autocorrelation as the data changes. Sometimes that shift is meaningful. Sometimes it is just reacting to noise. The real work is testing whether the attention patterns hold up out of sample or whether the model is just fitting structure that disappears the moment regime changes.

#MachineLearning #QuantFinance #Transformers #MarketData #SystematicTrading by @falaktb

1k

27

6 months ago

HFT economics are driven by scale. If the edge on each trade is small but the number of opportunities is large, lowering latency becomes worth an enormous amount of money. #HFT #QuantFinance #AlgorithmicTrading #MarketMicrostructure #Trading by @falaktb

556

18

6 months ago