Repository of NLP papers useful for applying NLP techniques to financial markets.
Direct applications of NLP research to financial markets.
- Analyzing Stock Market Movements Using Twitter Sentiment Analysis
- Deep Learning for Financial Sentiment Analysis on Finance News Providers
- Deep Learning for Stock Prediction Using Numerical and Textual Information
- Giving Content to Investor Sentiment: The Role of Media in the Stock Market
- The Impact of Structured Event Embeddings on Scalable Stock Forecasting Models
- Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
- More Than Words: Quantifying Language to Measure Firms’ Fundamentals
- Predicting Stock Market Movement with Deep RNNs
- Predicting Stock Movement through Executive Tweets
- Sentiment Analysis in Financial News
- Sentiment Predictability for Stocks
- Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFinText System
- Twitter mood predicts the stock market
- Natural Language Processing - Part 1: Primer
- An Analysis of Verbs in Financial News Articles and their Impact on Stock Prices
- Trading Strategies to Exploit Blog and News Sentiment
- From Word to Time Series Embedding
Fundamental NLP research that could find applications in the financial markets. Fundamental research on Question Answering could be applied to credit analysis (default probability given a set of documents). Document Classification could be applied to ESG analysis to predict whether a company is sustainable or not. Sentiment Analysis could be applied to predict the impact a given document will have on the stock price.
- Reading Wikipedia to Answer Open Domain Questions
- Ask Me Anything: Dynamic Memory Network for Natural Language Processing
- Neural Generative Question Answering
- Question Answering Using Deep Learning
- Convolutional Neural Networks for Sentence Classification
- Enriching Word Vectors with Subword Information
- Fine-tuned Language Models for Text Classification
- From Word Embeddings To Document Distances
- Neural Text Generation: A Practical Guide
- A Deep Reinforcement Model for Abstractive Summarization
- Domain Adaptation using Stock Market Prices to Refine Sentiment Dictionaries
- Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: Paper and Code
Contributions more than welcome :-)