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.
33 documents
The document introduces LangChain as a way to connect large language models with external data and compose repeatable analysis workflows. It explains basic components including model calls, prompt templates, chains, batching, and agents. Its equity-analysis…
This profile follows a California data analyst’s move toward quantitative and algorithmic trading. His engineering, econometrics, and data work led him to explore Python, futures, automated analysis, and discretionary trading based on macro news sentiment.…
The article distinguishes algorithmic trading, high-frequency trading (HFT), and news-based trading by their aims, time horizons, speeds, and data sources. It describes algorithmic systems as rule-based automation across varied horizons, HFT as speed-focused…
The article explains market sentiment as investors’ broad outlook, shaped by economic, fundamental, technical, and other information. It distinguishes momentum approaches that follow prevailing sentiment from contrarian approaches that anticipate a reversal…
The document outlines a conference about artificial intelligence, machine learning, and sentiment analysis in financial services. It describes research that processes news, social media, and other alternative data to classify sentiment and study its…
This webinar listing introduces sentiment analysis, also called opinion mining, as the computational classification of text opinions into positive, negative, or neutral attitudes. It frames the technique as potentially relevant to financial markets alongside…
This project builds a random forest regression model to estimate the next day’s EUR/USD closing price from daily price data, technical indicators, and Twitter sentiment. Predictors include OHLCV values, short and long EMAs, RSI, OBV, and daily mean sentiment…
The document introduces general and finance-tuned language models, then describes using natural language processing to turn financial text into sentiment measures. It outlines a workflow for collecting and preprocessing Federal Open Market Committee…
This overview introduces several methods for modeling financial data when a straight-line relationship is inadequate or the target is not a continuous average. It describes logistic regression for binary outcomes, including interpreting its output as a…
This article surveys an end-to-end approach to applying machine learning and artificial intelligence to trading. It advocates starting with a trading objective, selecting a model only when it adds value, and interpreting model outputs in the context of…
The document is a brief event report about a talk on quantitative news trading at a Princeton–UChicago quantitative trading conference. The speaker’s topic was how news articles can be quantified and whether trading strategies based on news analytics can be…
This article is a curated overview of resources on sentiment analysis for trading rather than a single strategy or empirical study. It points readers to approaches that use news, social media, earnings information, macroeconomic data, and other sources to…
The document explains share prices through the market’s changing expectations of future company earnings and business conditions. It uses an Indian automaker’s valuation expansion and later earnings growth to distinguish price gains driven by a higher…
The article describes three sentiment measures and proposes contrarian trades based on them. VIX is presented as an options-derived estimate of expected S&P 500 volatility; high readings are associated with fear and falling prices, while low readings are…
The document outlines conditions in which quantified news sentiment may be more useful for equity trading. It suggests that small-cap stocks can react more strongly than larger firms, low-beta stocks may be sensitive to sentiment shifts, and low-volatility…
The document introduces sentiment analysis, also called opinion mining, as a way to classify the tone expressed in text as positive, negative, or neutral. In a trading context, this can be applied to news and other unstructured information, which automated…
The article introduces spaCy as a Python library for processing text, with an emphasis on its production-oriented pipelines. It contrasts spaCy with NLTK and describes a workflow using a trained language model to convert text into tokens, lemmas, sentences,…
This guide explains VADER, a rule-based text sentiment tool that assigns word-level valence and combines it into a normalized compound score. It describes how the lexicon incorporates words, slang, and emoticons, and how sentence-level heuristics account for…
This article describes market sentiment as the collective outlook of participants and explains how text sentiment analysis attempts to classify opinions as positive, negative, or neutral. It outlines a workflow of collecting news, social media, or financial…
Tomás García-Purriños describes a medium- to long-term approach to multi-asset investing that combines technical indicators with fundamental measures, especially macroeconomic data, and indicators of investor sentiment and market flows. He argues that no…
The document defines the Arms Index, or TRIN, as the ratio of advancing stocks to declining stocks divided by advancing volume to declining volume. It interprets readings below 1 as generally bullish and readings above 1 as generally bearish, while unusually…
This article presents a basic text sentiment workflow for financial commentary using R. It applies a bag-of-words approach: prepare positive and negative term lists, clean an earnings-call transcript, tokenize it into words and n-grams, and compare the…
The article surveys data sources that can supplement price and volume analysis. It covers company ratios and financial statements, macroeconomic indicators, earnings dates, financial news, tweets, and sentiment scores. It names services and Python libraries…
This analysis uses daily Nifty 50 futures data from exchange files to examine price, trading volume, open interest, rollover percentages, and foreign and domestic institutional activity during the first quarter of 2020. It explains how to interpret price…