An Optimization Approach to Roster Creation

Abstract

In this session, we will explore roster construction through mixed-integer optimization. Using individual NBA player characteristics, we will formulate an optimization problem that constructs the ideal national basketball team subject to various constraints on team composition. This example will introduce a general framework for how to formalize various strategic problems (e.g. scheduling, pricing, staffing) as optimization models. These models will be implemented using JuMP in the Julia programming language.

Date
Event
Workshop
Location
Sloan Sports Analytics Conference 2020