Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
5,018 documents
The document asks how to predict whether bank customers will remain active, using their account movements, and points toward customer activity or churn analysis as the problem area. It recommends multinomial logit and probit models as statistical methods to…
The discussion responds to a request for learning materials on stock-price forecasting with artificial neural networks, LSTMs, regression, and other predictive methods. It recommends two practical books: one covering modern forecasting models, including…
The document describes a Liar’s Poker approach that uses the serial numbers on a player’s own bills to inform bids, then asks whether that aggressive escalation is optimal. The answers connect the game to liar’s dice, where players make claims about a hidden…
The document compares using an interest-rate level, a log change, a simple percentage change, or a first difference as a regressor alongside stock returns. One answer recommends beginning with the untransformed rate because it is itself a rate, while another…
The discussion checks whether a forecasting routine uses the correct observation for a one-step-ahead AR(1) conditional mean forecast. Its answer clarifies the time indexing: when the latest observed sample is at time t−1 and the forecast target is time t,…
The discussion examines limits of Sharpe-style returns-based analysis when fund exposures shift, especially for long-short strategies or data at daily and finer frequencies. Suggested alternatives include Lasso to shrink factor coefficients, Bayesian…
The document responds to a request for credible examples of machine learning in quantitative finance. It emphasizes that machine learning methods are general-purpose tools that can be applied to financial, economic, or other data, while noting that many…
The document compares White’s Reality Check with the Benjamini-Hochberg-Yekutieli procedure for screening a large set of backtested strategies against a benchmark. It describes the Reality Check as accounting for dependence among test statistics through…
The document lists a small set of quantitative trading competitions in response to a Singapore-based participant seeking opportunities beyond the International Quant Championship and SMU Alphathon. It mentions a stock-prediction model competition run by XTX…
The document examines claims that artificial neural networks outperform Black–Scholes in option pricing. The cited study generates Black–Scholes estimates using simplified inputs, including a closing spot price, fixed volatility and interest rate, no…
The document explains how to represent a Wiener process on a uniform time grid for simulation. Divide the interval into equal steps, then construct each sampled value by adding the next increment to the previous value, starting from zero. The increment over…
The document asks which machine learning and statistical methods candidates should prepare for quantitative researcher and developer interviews at hedge funds and proprietary trading firms. It situates the question alongside probability puzzles and coding…
The document asks whether a time-series model that chooses a fully invested long or short position could be trained by maximizing simulated terminal portfolio value instead of minimizing squared prediction error. It proposes simulating daily positions from…
The document asks whether bootstrap resampling should happen before strategy data mining or after a candidate strategy has been selected. It describes a monthly SPY and TLT rebalancing strategy tested over six years and 72 trades, reporting a backtest Sharpe…
The document asks how to formulate a Kalman filter for return-based style analysis, where a fund’s returns are related to factor returns and the factor exposures may change over time. It proposes modeling the beta coefficients as the hidden state, perhaps…
The document describes an LSTM trading model using RSI, MACD, a ratio of two exponential moving averages, and recent returns as inputs over a short history. It assigns separate long and short outputs based on whether a hypothetical trade reaches a…
The document considers statistical tools for testing whether historical changes in a market variable appear random, with the aim of identifying unusual patterns and consistency over time. It points to the NIST test suite, a collection originally used to…
The document argues that risk management can sit beside an ML or AI alpha model rather than trying to interpret its internal features. A separate portfolio controller can translate forecasts or directional signals into feasible positions, accounting for…
The document asks how to implement time-shifted power-law kernels used in a path-dependent volatility model. The model forms volatility from a baseline plus weighted past returns and weighted squared returns. Separate kernels assign the lag-dependent weights…
The discussion addresses a regression intended to explain gold using the VIX, the EUR/USD exchange rate, and a US real-rate index. The model uses ridge regression because its author selected a small, theory-informed set of factors, yet reports an adjusted…
The document asks how to search for predictive relationships between a target series and many candidate variables. Its example is an inverted, three-month-delayed variable that appears to lead stock prices, and the proposed application is predicting future…
The document considers ways to investigate fractal behavior and harmonic patterns in stock time series, with the broader aim of building trading systems. Its concrete suggestion is to fit a Daubechies wavelet and examine coefficients across scales at a fixed…
The document surveys research and practical ideas for using news, blogs, social media, and company reports to forecast equity returns or other financial variables. It describes vendor sentiment scores and studies that apply nonlinear models, including trees,…
The discussion explains why a trading desk’s non-stationary daily P&L does not by itself prove that next year’s P&L is unpredictable. A desk’s P&L may reflect strategies and exposures that differ from the return stream of an investible asset, so…