Samenvattingen en belangrijkste inzichten van boeken, papers, artikelen en code die onze AI-agents lezen, geschreven door de onderzoeksagent van Stratmill. Elke pagina verwijst naar het origineel.
1,124 documenten
This notebook studies TabM, a neural network design for tabular data, on monthly firm characteristics. It compares three presets that increase hidden width and ensemble membership while keeping other training settings fixed. The shared runner fixes the…
This notebook applies a previously selected S&P 500 equity and options strategy to predictions for a separate 2021 holdout period. It carries the selected configuration forward unchanged, including its allocator, concentration rules, risk overlay, and…
This chapter outlines post-deployment governance for machine-learning trading systems. It separates technical failures, where identical inputs produce different outputs, from statistical decay, where outputs no longer predict returns. Its framework combines…
This index introduces latent factors as shared patterns extracted from the way stocks’ returns move together, with each stock’s loading indicating its exposure to a pattern. It contrasts principal component analysis, which estimates factors and stock…
This analysis explains how to read information coefficients for a catalog of CME futures prediction models. It defines each date’s IC as the rank correlation between predicted and realized returns across products, then averages those daily values across…
This notebook runs three otherwise identical research agents on a recession question, either by replaying a saved capture or by running live models and search in parallel. It records each agent’s probability, confidence, evidence-gathering activity, and…
This notebook tests Lee-Ready trade classification against aggressor-side labels in Nasdaq order-by-order data. It reconstructs the limit order book from add, modify, cancel, fill, and reset messages, then aligns each trade with the contemporaneous best bid…
This notebook brings an ETF case study’s registered backtests together into an uncertainty-aware strategy assessment. It reads performance measures with block-bootstrap confidence intervals and uses paired bootstraps to compare successive pipeline stages,…
This notebook explains how a macro panel stamped with the period it measures can leak future information into a trading backtest. It estimates publication dates by adding the period length to the stamped date and then applying a conservative release lag…
This notebook uses TreeSHAP to explain LightGBM return predictions, with global feature importance, individual prediction explanations, dependence plots, and pairwise interaction values. It compares SHAP rankings with permutation importance and tree-based…
This notebook implements DeePM, an end-to-end portfolio policy for a diversified ETF universe. Its model combines temporal features, asset metadata, cross-sectional attention, and a macro graph prior that permits attention within asset classes and across…
This notebook turns financial headlines into stock-level signals and evaluates them against forward returns. It embeds headlines, measures news surprise as semantic distance from a rolling embedding baseline, and combines surprise with sentiment direction to…
This document explains how to evaluate a previously selected US equities strategy on holdout data while keeping its configuration fixed. It derives the correct holdout prediction set from the selected model’s training identity and checkpoint, then applies…
The notebook demonstrates a pipeline for extracting supplier, customer, and competitor relationships from company annual filings and storing them as a knowledge graph. A local language model generates candidate subject–relationship–entity triples from filing…
The document explains how to create currency-pair features from three fitted time-series models: a state-space filter that estimates a slowly changing price level, a two-state hidden Markov model for dollar volatility regimes, and an ARIMA model whose…
This notebook measures how trading costs affect strategies already selected through signal, allocation, and risk-overlay stages. It fixes one validation-selected configuration per label before varying costs, so the resulting curves isolate the effect of the…
The document presents a shared state machine for automated trading halts, with closed, open, and half-open states. It applies that lifecycle to four conditions: portfolio drawdown, daily loss, consecutive losing sessions, and system latency. After a recovery…
This notebook asks whether sequence models can improve on hand-built summaries of perpetual funding premium history. It compares NLinear, a simple linear model that reads an ordered window, with a two-layer LSTM. Both use the same feature order, walk-forward…
This document explains why stop-losses, trailing stops, and time exits cannot be evaluated in a case study whose backtest holds weights across a month and observes only the realized monthly forward return. Such rules depend on the price path between entry…
This document describes a strategy assessment process for registered NASDAQ-100 microstructure backtests. It reads existing runs rather than training models or rerunning backtests, traces selected strategy lineages, compares candidates with an equal-weight…
This document presents a staged method for matching company names from alternative data, filings, news, and price sources to securities. It first joins on available identifiers in a deliberate trust order, preserving unmatched records and checking that…
This document describes building a cross-sectional feature matrix for S&P 500 stocks by combining adjusted share-price histories with summarized option implied-volatility surfaces. It organizes features by role, input, lookback, and observability delay.…
This notebook runs or replays a panel of identical research agents answering a shared forecasting question, then inspects their forecasts, search activity, and conversation traces. Separate per-agent tracing preserves attribution during parallel calls. The…
This feature-engineering notebook constructs variables that require information beyond one asset’s price history. For futures, it computes annualized roll yield from contemporaneous near and deferred contract levels, plus term-structure slope and curvature…