คลังความรู้

This notebook declares and runs a double machine learning analysis of the variance risk premium’s effect on S&P 500 option returns to expiry. It makes the estimand, observed timing, confounders, temporal cross-validation setup, nuisance model, HAC covariance…

This document explains why a daily constant-maturity option series is not a return series for a position actually held. It selects same-strike, same-expiration call and put legs that pass liquidity, maturity, volatility-estimation, and delta filters, then…

This notebook applies TabM to a flat table of US stock features, positioning it between penalized linear models and tree ensembles. Each ensemble member shares a neural network backbone but has its own scaling vector and output layer; averaging member…

This notebook describes a supervised autoencoder that compresses ETF feature rows into a low-dimensional representation and predicts forward returns directly from that representation. Unlike a conditional autoencoder, it does not assume that returns arise…

This notebook fits ridge, lasso and elastic-net models to a broad set of established US stock characteristics, including value, profitability, investment, momentum, size, risk and liquidity measures. It evaluates raw monthly returns, a cross-sectionally…

This analysis compares registered ETF prediction models across several families on a shared cross-asset panel. It evaluates how well each model ranks funds by subsequent returns using information coefficients, examines confidence intervals and fold-level…

This analysis applies correlation-based principal component analysis to returns from sector exchange-traded funds. Standardizing returns before decomposition gives each sector unit variance, so the leading components describe co-movement rather than being…

This utility computes selection-bias and performance uncertainty metrics for groups of strategy backtests. It forms cohorts at family, stage-and-label, and label granularity, then calculates measures including deflated Sharpe ratios, effective trial counts,…

This notebook describes how to parse IEX DEEP historical feed messages and maintain a limit order book using aggregated price-level updates. It extracts depth changes, best bid and ask quotes, and trade reports, then uses reconstructed snapshots to examine…

This analysis explains how CME futures data is organized into products, expiring contracts, and volume-rolled continuous series. It uses E-mini S&P 500 data to show how individual contracts have finite trading windows that overlap around a roll, while a…

This document describes implementation principles for a shared backtest runner and focuses on interpreting return grids correctly when annualizing performance. It estimates the observed sampling frequency from typical gaps between return observations,…

This notebook compares equal-weight, positive-score-weighted, and conformal-width-weighted allocations for top-ranked ETFs and CME futures. It estimates entity-specific split-conformal interval widths from residuals in earlier validation folds, excluding…

This notebook compares three ways to convert signed return predictions into binary positions: a fixed zero cutoff, a trailing percentile of each symbol’s own scores, and a cross-sectional percentile across symbols. It measures signal activation and state…

This document presents a supervised autoencoder as a control for conditional latent-factor models. It maps firm characteristics directly to forward returns while compressing 57 inputs through a narrow bottleneck. Comparing it with a conditional autoencoder…

This notebook explains how stock splits and cash dividends disrupt raw historical price series and distort calculated returns. It demonstrates backward adjustment, in which historical prices are rescaled for subsequent corporate actions, and applies the…

This notebook uses ETF features and forward returns to demonstrate classical ordinary least squares inference before turning to prediction-focused methods. It examines coefficient tests and standard errors, then diagnoses heteroscedasticity, residual…

This NASDAQ-100 study examines how transaction costs affect a frequently rebalanced equity strategy. It separates two possible responses to costs: restricting the traded universe to more liquid, lower-cost names, and reducing rebalance frequency. Keeping…

This experiment combines validation predictions from a gradient-boosted tree model, a tabular neural network, and a latent-factor model for monthly ETF ranking. It first standardizes predictions cross-sectionally with z-scores, then averages them. The…

This document presents shared methods for generating fitted-model features without using future observations. For hidden Markov models, it distinguishes filtered state probabilities, based on observations up to the current time, from smoothed probabilities…

This document describes a walk-forward method for turning prediction residuals into per-entity uncertainty widths used to size positions. At each decision time, calibration uses residuals that have had time to resolve, with a lag based on the prediction…

This case study selects one configuration from a frozen pool of crypto perpetual futures strategies spanning multiple return and direction labels, portfolio sizing methods, and risk overlays. It chooses the highest validation Sharpe, then examines…

This guide describes public factor return datasets from the Ken French Data Library and AQR, including market, size, value, profitability, investment, momentum, quality, and low-beta factors. It explains how to download and load monthly or daily…

This notebook uses double machine learning to estimate whether deviations in perpetual-futures premiums relate to subsequent eight-hour returns, and whether the estimated relationship differs between high- and low-volatility markets. It describes a panel…

This notebook presents PCMCI as a way to discover lagged relationships in multivariate financial time series without specifying a causal graph in advance. It applies the method to ETF and volatility-index returns, compares its conditional analysis with…