Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
4,510 documents
This sentiment-based strategy monitors a Fear and Greed Index and trades when its state crosses preset boundaries. It opens a long when the index enters the greed zone above 75 and closes that position when the index enters the fear zone below 25. The source…
This strategy estimates directional participation by assigning each bar’s volume to the up or down side according to whether its close rose or fell from the prior close. It smooths both volume series, divides up volume by down volume, and rescales the ratio…
This workflow describes an automated approach to tokenized US stock perpetual contracts. On a scheduled cycle, it collects current position details, news sentiment, and daily US equity candles. It computes MACD, RSI, ATR, and OBV, then uses language-model…
This workflow automates a dollar-cost averaging process for cryptocurrency spot purchases. On a recurring hourly cycle, it gathers market data to calculate MACD, RSI, ATR, and OBV, and retrieves recent crypto news for AI-based short- and long-term sentiment…
This Polymarket strategy screens event contracts for liquidity, trading activity, spread, market competitiveness, and price, then scores hourly candlestick patterns such as gradual rises, growing volume, narrowing pullbacks, and breakouts. Candidates passing…
This workflow describes a two-sided grid for crypto derivatives. It places long entries at descending price levels and short entries at ascending levels, with each position intended to close for a profit when price returns by one grid step. A minute-level…
This strategy converts candlestick patterns into three sentiment measures: indecision from doji and spinning-top candles, fear from bearish reversal patterns, and greed from bullish patterns. Their average forms a Candle Emotion Index. The source triggers…
This indicator estimates market sentiment by dividing smoothed price changes by smoothed volume, then applying fast and slow exponential averages to that ratio. Their difference forms a MACD-like line, with a signal average and histogram. In the supplied…
The described framework combines predefined support and resistance levels, bullish and bearish sentiment thresholds, and a candlestick feedback condition to trigger long or short entries. It also presents a risk-reward target and position sizing based on…
This strategy adapts the Finite Volume Elements indicator by comparing a money-flow measure with a threshold derived from intraday and interday volatility variability. It computes a flow value from changes in price medians, then assigns positive, negative,…
This proposed intraday strategy combines Nifty 50 price levels with changes in open interest. It takes a long signal when price is below a specified support level and open interest is above its moving average by more than a buy threshold. It takes a short…
This TradingView script tracks daily changes in large holders’ aggregate crypto assets using IntoTheBlock data. It compares each change with a 21-period Bollinger Band calculated from those changes, then marks positive moves above the upper band as purchases…
This document presents a visual revision of a dual VADER indicator. It retains the underlying calculations from an earlier version, while displaying the longer-period sentiment measure as an area and representing demand and supply energy as directional bars.…
The document presents a contrarian idea: take the opposite side of a machine learning system’s probability forecast derived from financial news. If its signal indicates a likely rise, the strategy sells; if it indicates a likely decline, it buys. The example…
This chapter surveys financial text representations, from dictionaries and word counts through TF-IDF, static embeddings, recurrent networks, and Transformers. It explains the trade-offs: simpler methods are fast, interpretable, and adaptable to finance,…
This reference describes the Financial Phrasebank, a labeled collection of financial news sentences used to train or evaluate natural language processing models. Human annotators assign positive, neutral, or negative sentiment labels. The corpus is available…
This notebook shows how to turn quarterly SEC 10-Q Management’s Discussion and Analysis text into two candidate equity signals. FinBERT scores text chunks for positive, neutral, or negative tone; chunk scores are aggregated into average sentiment and…
This notebook compares three ways to classify financial-news sentences as positive, neutral, or negative: TF-IDF word and phrase features with logistic regression, averaged static word vectors with a classifier, and a pretrained FinBERT sentiment model.…
This notebook presents a workflow for turning SEC annual and quarterly filings into structured text suitable for later sentiment, topic, and embedding analysis. It maps desired sections to form-specific item numbers, emphasizing that management discussion…
This reference describes two financial news corpora used for sentiment analysis, text-feature development, and experiments linking news to returns. FNSPID connects headlines with stock tickers and covers a broad historical span; a smaller sample is available…
This document describes a workflow for turning quarterly SEC 13F bulk filings into an institutional holdings panel. It selects the latest filing per manager by filing date, uses CUSIP rather than filer-entered company names to identify securities, and…
This notebook demonstrates fine-tuning a transformer for financial named entity recognition, turning text spans into structured organization, person, money, date, and percentage fields. It introduces BIO boundary labels and explains how word-level…
This notebook evaluates security rules for a document-grounded financial assistant using six hand-built cases. The cases cover prompt injection, fabricated figures in untrusted material, attempted actions, and citations to content that was not retrieved. Two…
This notebook trains a Skip-gram Word2Vec model on a small, sentiment-labeled financial news corpus and examines what its nearest neighbors reveal. The method represents words based on the contexts in which they appear. In the example, profit and loss become…