Knowledge library

This notebook surveys methods for detecting changes in a financial time series, using SPY as an example. It contrasts the Zivot–Andrews test, which estimates one break while testing a unit-root hypothesis, with PELT and binary segmentation, which partition a…

This notebook evaluates a pretrained financial sentiment model on FinMarBa headlines and explains why the result is not a clean test of sentiment transfer. FinBERT was trained against human judgments of text sentiment, while FinMarBa’s negative, neutral, and…

This notebook compares weekly-grid sequence models for predicting the same five-session forward return used on a daily grid. Sampling on Fridays makes that label approximately a one-step-ahead target, allowing a direct regression formulation to be compared…

This notebook builds a retrieval-augmented research assistant over excerpts from US company 10-K filings. It loads filings, splits text into sentence windows, embeds the chunks with a local model, and indexes them for similarity search. The demonstrated run…

This notebook demonstrates training a generative adversarial network on daily ETF features with differential privacy. It introduces the privacy guarantee and budget, then uses Opacus to clip each sample's discriminator gradient before aggregating gradients…

This notebook applies TabM, a weight-sharing neural ensemble, to stock-return targets built from equity-option features. Its members use a common two-layer network backbone, with separate activation scaling vectors and output heads whose predictions are…

This chapter surveys ways to generate synthetic financial data and how to decide whether the output is useful. It starts from the limited number of realized market paths and the risk that repeated strategy searches inflate apparent backtest performance. It…

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 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 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 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 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 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…

This notebook explains how to evaluate probability forecasts and govern a forecasting pipeline. It compares Brier and log scores, expected calibration error, and sharpness; shows how reliability diagrams reveal where forecasts are over- or under-confident;…

This deployment demonstration retrains a Ridge model on historical daily data for a cross-section of major FX pairs, fetches current bars through an Interactive Brokers paper session, ranks the pairs, and builds a long basket. It walks through connecting to…

This tutorial turns ETF cross-sectional signals into long-only, equal-weight top-ten portfolios and compares Ridge regression and logistic classification with momentum and equal-weight baselines. Models are fitted on walk-forward training windows, with a…

This study tests whether the poor fit of a linear model to monthly US stock returns comes from its squared-error objective. It holds the unwinsorized forward-return target, features, and walk-forward folds fixed while comparing boosted tree models trained…

This notebook trains a Proximal Policy Optimization agent to liquidate a fixed order over a set horizon. It compares the learned pacing policy with TWAP and an Almgren–Chriss schedule, measuring implementation shortfall and examining when each strategy…