Two-Sided Matching to Achieve Win-Win

Zoom Link for Virtual Attendees
https://renci.zoom.us/j/95304314757?pwd=YzFwdHp2VGVqVjFuSFBObmpiRGNkZz09

Victor Lo and Ping Yao of Fidelity Investments will describe their cutting-edge research on using two-sided matching algorithms to for win-win optimization.

Doors Open at 6:00pm
Presentation starts at 6:30pm

This will be a hybrid event--online and in person. Our speakers will be remote.

For many business applications, statistical analysis or machine learning is commonly employed to help optimize an objective. While successful in practice, this approach is one-sided, typically from the developer or corporate perspective which may not necessarily be beneficial to the target audience (e.g., customers, employees). In this paper, we propose a mutually beneficial approach using two-sided matching. Consider the following two cases.

Customer-Product Matching in Marketing: Product recommendation engines are often developed by corporations to maximize customer purchase or engagement by selecting customers who are most responsive to a product offer or marketing intervention. On the other hand, the literature is not short of a customer-centric approach where customer’s interest should be considered first. If customer preference or experience can be quantified (e.g., through surveys) or inferred (e.g., based on historical interactions), one can train a model to recommend the right products such that customer preference or value to customer is maximized. How do we integrate the models to drive both value to customer and value to business?

Employee-Project Matching in Project Assignment: If a firm has a group of employees with certain skills (e.g., data scientists) and a large number of projects, how should the employees be assigned to projects? Often it is based on historical experience, skills, and availability, which are important factors to drive success aided by statistical analysis or predictive/prescriptive analytics that benefits the firm. However, listening to employees and tailoring value propositions to their needs and preferences are a good management practice. If employees’ perspective is taken as a priority, their interests can be captured to construct a machine learning or rule-based model. How would we resolve the potential conflict of interest by addressing both employee and corporate interests to achieve a win-win?

In many applications such as the above, interests from both sides may be considered as a value exchange: the provider and the receiver or the seller and the buyer, where each side has some value to offer to the other side. We propose an approach using the deferred acceptance algorithm in conjunction with statistical modeling and machine learning. A key desirable property is that the solution is shown to achieve “stability” in the sense that no pair of agents (customer/product, employee/project in our cases) would prefer each other to their match recommended by the algorithm.