New Method for Pinpointing Breaks in Economic Trends
Researchers from the Centre for Big Data in Economics and Finance have developed a new method for accurately identifying structural breaks in economic and financial time series. Their paper, "Change-Point Detection in Time Series Using Mixed Integer Programming," introduces a framework based on Mixed Integer Optimization (MIO).
Researchers from the Centre for Big Data in Economics and Finance (Artem Prokhorov, Peter Radchenko, Alexander Semenov, Anton Skrobotov) have developed a new method for accurately identifying structural breaks in economic and financial time series. Their paper, “Change-Point Detection in Time Series Using Mixed Integer Programming” (arxiv), introduces a framework based on Mixed Integer Optimization (MIO).
Abstract:
We use cutting-edge mixed integer optimization (MIO) methods to develop a framework for detection and estimation of structural breaks in time series regression models. The framework is constructed based on the least squares problem subject to a penalty on the number of breakpoints. We restate the
l0-penalized regression problem as a quadratic programming problem with integer- and real-valued arguments and show that MIO is capable of finding provably optimal solutions using a well-known optimization solver. Compared to the popular l1-penalized regression (LASSO) and other classical methods, the MIO framework permits simultaneous estimation of the number and location of structural breaks as well as regression coefficients, while accommodating the option of specifying a given or minimal number of breaks. We derive the asymptotic properties of the estimator and demonstrate its effectiveness through extensive numerical experiments, confirming a more accurate estimation of multiple breaks as compared to popular non-MIO alternatives. Two empirical examples demonstrate usefulness of the framework in applications from business and economic statistics.
The proposed framework reformulates the change-point detection problem into a Mixed Integer Quadratic Programming task, which allows modern solvers to find a proven optimal solution. A key advantage over methods like LASSO is its ability to simultaneously and directly estimate the number of breaks, their locations, and the regression coefficients in a single step. The method's effectiveness is confirmed through numerical experiments, where it showed superior performance, especially in scenarios with multiple breaks. Its practical utility was demonstrated in two applications: analyzing US real interest rates, where it identified shifts linked to historical events, and an inventory adjustment model, where it provided new insights into the speed of economic responses.
