2017/04/27 by Dieter Hendricks, Stephen Roberts, Hendricks, Dieter +1 · 1 citation
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Financial Markets and Investment Strategies #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Stock Market Forecasting Methods #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1704.08488
openalex publication_date 2017/04/27 · openalex created_date 2022/09/27 · openalex updated_date 2026/07/28
The process of liquidity provision in financial markets can result in\nprolonged exposure to illiquid instruments for market makers. In this case,\nwhere a proprietary position is not desired, pro-actively targeting the right\nclient who is likely to be interested can be an effective means to offset this\nposition, rather than relying on commensurate interest arising through natural\ndemand. In this paper, we consider the inference of a client profile for the\npurpose of corporate bond recommendation, based on typical recorded information\navailable to the market maker. Given a historical record of corporate bond\ntransactions and bond meta-data, we use a topic-modelling analogy to develop a\nprobabilistic technique for compiling a curated list of client recommendations\nfor a particular bond that needs to be traded, ranked by probability of\ninterest. We show that a model based on Latent Dirichlet Allocation offers\npromising performance to deliver relevant recommendations for sales traders.\n