Insights Live: Boston Digital Leadership Forum: Can Machine Learning Improve Human Decision-making?
Workers spend a significant amount of time learning how to make good decisions. The learning process is challenging because outcomes are often long-term and relate to the original decision in complex ways, making it hard to evaluate the efficacy of a given decision. The goal of our research is to study whether machine learning can be used to infer tips that can help workers learn to make better decisions. Such an algorithm must identify strategies that not only improve worker performance, but that are also interpretable to the human workers so that they can easily understand and follow the tips. We propose a novel machine learning algorithm for inferring interpretable tips that can help users improve their performance in sequential decision-making tasks. We perform a behavioral study to validate our approach. An important ingredient in our managerial framework is the incorporation of trace data to identify pieces of information that are most likely to help improve the performance of an average worker. Modern-day organizations have benefited from using customer data to inform new product strategies and provide personalized offerings to their customers, but the data on their own employees is underused. Our framework provides techniques to leverage the largely untapped potential of readily available trace data in pinpointing areas of performance improvement and identifying new practices. Even when the true optimal strategy is unknown, trace data of workers with high experience or good performance can be used to identify good strategies. In recent years, a growing number of organizations have adopted a gig economy employment model or allowed for remote work in response to worker preferences for flexibility and independence. To compensate for the lack of interactions among workers, firms can employ our algorithm to learn best practices from the highly performing workers and then provide tips to help individuals improve.