We implement an efficient methodology for extracting themes from Securities Exchange Commission 13D filings using aspects of human‐assisted active learning and long short‐term memory (LSTM) neural networks. Sentences from the ‘Purpose of Transaction' section of each filing are extracted...

Using a small sample of sentences, I test the performances of three models in predicting sentence sentiment (positive, neutral, or negative): a simple model based on a financial word list, a simple neural network model based on vector representations of words, and a sentence-based neural network...

A single hidden layer neural network can be trained to predict whether a stock will be in the top, middle, or bottom third of sample stocks based on its return over the next month based on return, trading volume, and volatility measures available at the end of this month. In my preliminary work...

This paper tests whether net order flow (or signed trading volume, the difference between public buy order volume and public sell order volume) helps predict short term future returns. It finds that net order flow does not explain daily and weekly return autocovariances. Thus, short term return...