Cognitive User Interface for Portfolio Optimization

This paper describes the development of a chatbot as a cognitive user interface for portfolio optimization. The financial portfolio optimization chatbot is proposed to provide an easy-to-use interface for portfolio optimization, including a wide range of investment objectives and flexibility to include a variety of constraints representing investment preferences when compared to existing online automated portfolio advisory services. Additionally, the use of a chatbot interface allows investors lacking a background in quantitative finance and optimization to utilize optimization services. The chatbot is capable of extracting investment preferences from natural text inputs, handling these inputs with a backend financial optimization solver, analyzing the results, and communicating the characteristics of the optimized portfolio back to the user. The architecture and design of the chatbot are presented, along with an implementation using the IBM Cloud, SS&C Algorithmics Portfolio Optimizer, and Slack as an example of this approach. The design and implementation using cloud applications provides scalability, potential performance improvements, and could inspire future applications for financial optimization services.

[1]  Stephen J. Cox,et al.  Analysis of User Interaction with Service Oriented Chatbot Systems , 2007, HCI.

[2]  Kenneth Mark Colby,et al.  Artificial Paranoia , 1975, Artif. Intell..

[3]  Helmut Mausser,et al.  Computing equal risk contribution portfolios , 2014, IBM J. Res. Dev..

[4]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[5]  Peter A. Gloor,et al.  In bot we trust: A new methodology of chatbot performance measures , 2019, Business Horizons.

[6]  Asbjørn Følstad,et al.  Why People Use Chatbots , 2017, INSCI.

[7]  Francesco Colace,et al.  Chatbot: An Education Support System for Student , 2018, CSS.

[8]  Ying Chen,et al.  IBM Watson: How Cognitive Computing Can Be Applied to Big Data Challenges in Life Sciences Research. , 2016, Clinical therapeutics.

[9]  K. Brown,et al.  The Use and Value of Financial Advice for Retirement Planning , 2020 .

[10]  Sabri Pllana,et al.  PAPA: A parallel programming assistant powered by IBM Watson cognitive computing technology , 2018, J. Comput. Sci..

[11]  Matthew B Hoy.  Alexa, Siri, Cortana, and More: An Introduction to Voice Assistants , 2018, Medical reference services quarterly.

[12]  Ashok Goel,et al.  Using Watson for Constructing Cognitive Assistants , 2016 .

[13]  Daniel Baier,et al.  Chatbots in retailers’ customer communication: How to measure their acceptance? , 2020 .

[14]  Bernhard Knapp,et al.  An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot , 2020, Scientific reports.

[15]  Helmut Mausser,et al.  Chapter 12: Applications of Conic Linear Optimization in Financial Engineering , 2017 .

[16]  David A. Ferrucci,et al.  Introduction to "This is Watson" , 2012, IBM J. Res. Dev..

[17]  Helmut Mausser,et al.  Using Trading Costs to Construct Better Replicating Portfolios , 2010 .

[18]  Teodoro D Cocca.  Potential and Limitations of Virtual Advice in Wealth Management , 2016 .

[19]  Adam S. Miner,et al.  Chatbots in the fight against the COVID-19 pandemic. , 2020, NPJ digital medicine.

[20]  J. Michael Collins,et al.  Financial Advice: A Substitute for Financial Literacy? , 2012 .

[21]  Alison Lui,et al.  Artificial intelligence and augmented intelligence collaboration: regaining trust and confidence in the financial sector , 2018, Information & Communications Technology Law.

[22]  Helmut Mausser,et al.  Robust scenario-based value-at-risk optimization , 2016, Ann. Oper. Res..