Deep Prediction Of Investor Interest: a Supervised Clustering Approach

Baptiste Barreau (1, 2) , Laurent Carlier (2) , Damien Challet (1)

1 MICS - Mathématiques et Informatique pour la Complexité et les Systèmes
2 BNPP CIB GM Lab - BNP Paribas CIB Global Markets Data & AI Lab

We propose a novel deep learning architecture suitable for the prediction of investor interest for a given asset in a given timeframe. This architecture performs both investor clustering and modelling at the same time. We first verify its superior performance on a simulated scenario inspired by real data and then apply it to a large proprietary database from BNP Paribas Corporate and Institutional Banking.

Mots clés: investor activity prediction; deep learning; neural networks; mixture of experts; clustering

Domaines: Apprentissage [cs.LG]; Finance quantitative [q-fin.CP]; Machine Learning [stat.ML]

Baptiste Barreau, Laurent Carlier, Damien Challet. Deep Prediction Of Investor Interest: a Supervised Clustering Approach. Algorithmic Finance, 2021, 8 (3-4), pp.77-89. ⟨10.3233/AF-200296⟩. ⟨hal-02276055v3⟩