Knowledge library

This notebook examines whether SHAP feature attributions are stable enough to support model pruning, risk decisions, or reporting. Using an ETF prediction task, it first searches for test samples whose predictions are close while their SHAP profiles differ.…

This configuration describes a daily, long-short US equity strategy that ranks a broad stock universe by model predictions, buys the top decile, and shorts the bottom decile with equal weights within each group. It specifies next-session open execution,…

This notebook evaluates candidate features for 20 currency pairs one at a time against forward returns. It limits the analysis to walk-forward validation periods, stamps each session with its fold, and leaves a buffered gap before the holdout so labels…

This notebook explains how to combine probability forecasts from multiple agents and how to calibrate the resulting probabilities. It presents Neyman extremization, which moves the mean forecast away from a base rate according to panel size and an assumed…

This data utility supports work with the Chen, Pelger, and Zhu asset-pricing dataset, which includes stock returns, firm characteristics, macroeconomic series, and pre-split characteristic tensors. Its conversion method builds Parquet files from the…

This notebook turns model rankings into simple crypto perpetual portfolios. At each funding timestamp, an entry rule selects contracts from the top or bottom of the ranking and assigns equal weights. Equal weighting provides a reference point: comparisons…

This notebook examines whether financial features help explain a 10-session delta-hedged options return label. It compares Ridge models using one implied-volatility feature, groups of implied-volatility-dependent and independent features, and the full…

This notebook measures how validation Sharpe for at-the-money S&P 500 option straddles changes across assumed execution costs and two option universes. It expresses spread cost as a fraction of the quoted option half-spread, since option premium and…

This module describes a shared way to prepare walk-forward training and validation folds for multiple model families. It separates expensive, model-independent work—slicing time windows, applying fold-specific model-based features, removing rows with missing…

This notebook evaluates LSTM and NLinear sequence models for futures forecasting. Unlike models that use one feature row per decision, sequence models consume ordered windows of past observations, potentially learning patterns that fixed summaries miss.…

This notebook compares validation predictions from multiple model families for perpetual-futures funding research. It explains that information coefficient measures rank association between predictions and subsequent returns, AUC measures ranking for up or…

This implementation describes how to construct batched sequence windows for panel data used in deep-learning studies. Windows follow the panel’s expected calendar rather than compressing each asset’s observations into consecutive rows. Missing sessions…

This notebook presents practical cleaning methods for market and firm data, including duplicate handling, gap flags, domain filters, reversal-based spike detection, outlier clipping, categorical encoding, and alignment across datasets with different…

This notebook explains how to assess whether strategies built on a US equities panel can withstand trading friction. It fixes one configuration per label using validation Sharpe, then reprices that same strategy across declared cost levels. This prevents the…

This notebook examines whether SHAP attributions remain stable when predictions are similar or when models are refitted with different random seeds and architectures. Using ETF forward returns, it searches for sample pairs whose predictions are close but…

This notebook fits gradient-boosted tree models to options-market features that encode forecasts such as implied volatility, skew, term structure, and variance risk premium. It compares tree capacity and regression loss choices across forward-return and…

This notebook connects position sizing with analysis of maximum adverse and favorable excursions. It demonstrates fixed-fractional sizing, where shares are determined by a portfolio risk budget and entry-to-stop distance, with a cap on position…

This notebook compares Polymarket’s crypto-settled event contracts with Kalshi’s regulated contracts, focusing on how access rules and listing policies shape the prices and questions each venue represents. It inspects a small Polymarket snapshot, checks how…

This case study tests weekly long-short carry-ranked strategies across a diversified set of CME futures, using daily data, walk-forward model evaluation, and costs for commissions, spreads, and roll slippage. It compares signal quality across model families,…

This document explains how to represent a live order’s lifecycle as a finite set of states and valid event-driven transitions. It covers submission, broker acknowledgment, exchange acceptance, partial and full fills, cancellation requests, rejection, expiry,…

This notebook compares predictive, structural, and causal model evidence for a cross-sectional S&P 500 study combining equity features with options-derived measures such as implied volatility, skew, and term structure. It evaluates weekly forward-return…

This notebook shows how to translate gross returns into net performance under explicit trading, financing, and fund-expense assumptions. Its cost stack includes spread and market impact, commissions and exchange fees, margin interest, stock borrow,…

This notebook demonstrates a trade-level diagnostic workflow that links realized failures to a model’s SHAP explanations. It trains a LightGBM model on lagged price and volatility features plus macro inputs to forecast next-session SPY returns. A fixed…

This notebook compares behavior cloning with inverse reinforcement learning (IRL) for learning from execution records. Its demonstrations come from a TWAP schedule, whose risk-neutral objective is known: spread trades evenly to limit impact while accepting…