Financial Robo-Advisor: Learning from Academic Literature

A Decision-Theoretic Academic Advisor: Extended Abstract

This paper describes work related to stochastic modeling and decision-theoretic (DT) planning methods applicable to the real-world domain of academic advising. The uncertainty associated with stochastic planning is often approached as a problem of finding a complete mapping from states to actions (a policy). A need to plan for all contingent futures makes (DT) planning an inherently difficult p...

The Bayesian Advisor Project: Modeling Academic Advising

An academic advisor's job requires that the advisor knows university and departmental requirements; available courses to satisfy those requirements, and a method for predicting relative student success for various course options. Such predictions are necessarily uncertain, both because the advisor has limited information about the student and because student performance can be in-uenced by unfo...

Literature review on advisor selection

How analytical is your financial advisor?

We survey over 100 financial planners to assess their reasoning mode, intertemporal choices, risk aversion and preferences, and framing focus. Using the Cognitive Reflection Test, we find that financial planners are more analytical than the general population. Further tests show that the analytical planners are more financially patient and perform better in intertemporal choice problems. These ...

Multi-Advisor Reinforcement Learning

This article deals with a novel branch of Separation of Concerns, called Multi-Advisor Reinforcement Learning (MAd-RL), where a single-agent RL problem is distributed to n learners, called advisors. Each advisor tries to solve the problem with a different focus. Their advice is then communicated to an aggregator, which is in control of the system. For the local training, three off-policy bootst...