Deep Prediction of Investor Interest: a Supervised Clustering Approach
This work addresses the problem of predicting investor interest for financial institutions, but it appears incremental as it builds on existing deep learning and clustering methods without claiming broad breakthroughs.
The paper tackles predicting investor interest for assets by introducing a deep learning architecture that simultaneously clusters investors and models their behavior, demonstrating superior performance on synthetic data and applying it to two real-world datasets, including Spanish stock market data and proprietary BNP Paribas data.
We propose a novel deep learning architecture suitable for the prediction of investor interest for a given asset in a given time frame. This architecture performs both investor clustering and modelling at the same time. We first verify its superior performance on a synthetic scenario inspired by real data and then apply it to two real-world databases, a publicly available dataset about the position of investors in Spanish stock market and proprietary data from BNP Paribas Corporate and Institutional Banking.