Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
1,124 dokumenttia
This notebook examines how to combine multiple probability forecasts. It presents simple averaging as a baseline and explains Neyman extremization, which moves a panel mean farther from a base rate according to the number of forecasters and an assumed…
This notebook compares daily, weekly, biweekly, and monthly rebalancing for a top-ranked momentum portfolio built from a fixed ETF universe. It measures turnover and gross risk-adjusted performance from historical prices, then estimates break-even alpha by…
This notebook turns futures carry—the price gap between nearby expiries—into model-based features. It describes one-step ARIMA forecasts per product, rolling Fourier measures of seasonal cycle strength, and a two-state hidden Markov model that infers broad…
This configuration module describes a framework for declaring backtest sweep settings per case study. It reads entry schemes, allocation methods, trading cost grids, and risk controls from setup files, with explicit errors when required configuration is…
This overview explains a family of models for predicting returns from firm characteristics. Rather than treating each characteristic as a direct return predictor, the models assume returns are driven by a small set of unobserved common factors and estimate…
The notebook presents a reporting method for a long-only RSI mean-reversion strategy on BTC. It compares gross and net performance, then benchmarks the strategy against buy-and-hold using the same trading dates, exposure, execution engine, fill timing, and…
This setup document defines a weekly S&P 500 equity research pipeline that uses options market features alongside price-based signals. It specifies the eligible universe, decision and execution timing, and distinct rebalance cadences for labels with…
This document presents a pedagogical Mamba-style selective state space model for predicting ETF returns from sequences of momentum features. Unlike attention and dense temporal mixing, a state space model carries a fixed-size state through the sequence with…
This document describes a conditional autoencoder that models firm exposures to latent return factors as a nonlinear function of firm characteristics. Like IPCA, it estimates a factor structure in which predicted returns combine firm-specific exposures with…
This document explains a TabM neural network for ranking ETFs from tabular features. Its shared two-layer backbone feeds multiple members, each with a learned scaling vector and output layer; averaging their predictions aims to reduce initialization noise…
This notebook explains how volume participation limits constrain the portion of market volume an order can consume in each interval. When a parent order exceeds the permitted amount, the broker fills part of it and carries the remainder forward. A…
This chapter overview explains how gradient-boosted trees build on decision trees and random forests for financial tabular prediction. Boosting adds learners sequentially to correct earlier errors, helping capture nonlinear relationships and threshold…
This document describes a monthly US equity dataset designed for machine learning research in asset pricing. It contains 94 rank-transformed firm characteristics, including accounting measures and technical features, alongside returns. Firms are anonymized,…
This notebook examines how market impact changes a momentum strategy’s backtest results across stocks with different liquidity. It holds the order size and strategy constant, estimates liquidity and volatility from a formation period, and applies several…
This notebook evaluates security controls for a financial document question-answering system using six hand-written cases. The cases represent indirect prompt injection, fabricated data in untrusted material, attempted actions, and invalid citations. It…
This notebook introduces a published panel for machine-learning research on US equities. It contains monthly observations with 46 firm characteristics and next-month excess returns, spanning several decades. The characteristics are grouped by economic…
This chapter explains how to build and use financial knowledge graphs when questions depend on relationships such as ownership, supply chains, or contagion. It covers entity identity, typed relationship schemas, provenance, and LLM-assisted extraction from…
This notebook compares two Transformer designs for forecasting 21-day ETF returns from eight trailing-momentum features. PatchTST groups consecutive days into patches, reducing the number of attention tokens and embedding local time patterns. iTransformer…
This notebook analyzes a portfolio of equity ETFs with CAPM and Fama-French factor regressions, then expands the analysis to rolling exposures, return attribution, and residual dependence. It uses aligned daily returns and factor data, estimates regression…
This document explains fractional differencing as a way to make a price series more stationary while retaining some information about its level. It derives the lag weights from the binomial expansion of a fractional difference and shows how truncating small…
This notebook assesses whether four-hour spot FX data can support a daily cross-sectional strategy that ranks currency pairs using momentum and carry, buys the strongest, and sells the weakest. It does not fit a model or make forecasts. Instead, it checks…
This demonstration runs one dual moving-average crossover strategy through both a historical backtest engine and a live engine replaying the same daily ETF bars. It holds the strategy, inputs, parameters, and fill convention fixed, then compares the…
This notebook compares squared error, absolute error, and Huber loss for gradient-boosted models predicting short at-the-money straddle returns. The target has a capped gain and potentially severe losses, so the fitting loss may affect how well predictions…
This notebook turns hourly continuous futures data into daily OHLCV bars aligned to CME Globex sessions. It assigns timestamps to the session ending at 4 PM Central Time, so Sunday evening trading belongs to Monday and Friday evening does not create a…