Deep prediction of investor interest: A supervised clustering approach

Article type: Research Article

Authors: Barreau, Baptiste^{a; b; *} | Carlier, Laurent^b | Challet, Damien^a

Affiliations: [a] Chair of Quantitative Finance, MICS Laboratory, CentraleSupélec, Université Paris-Saclay, Gif-sur-Yvette, France | [b] BNP Paribas Corporate & Institutional Banking, Global Markets Data & Artificial Intelligence Lab, Paris, France

Correspondence: [*] Corresponding author: Baptiste Barreau. E-mail: baptiste.barreau@bnpparibas.com.

Note: [1] Code is available at https://github.com/BptBrr/deep_prediction

Note: [2] Data is available at https://zenodo.org/record/2573031

Abstract: 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.1,2

Keywords: investor activity prediction, deep learning, neural networks, mixture of experts, clustering

DOI: 10.3233/AF-200296

Journal: Algorithmic Finance, vol. 8, no. 3-4, pp. 77-89, 2020