Automating Demand Forecasting For Major Logistics Company
While logistics is a fairly mature, technologically-advanced, and analytically-sophisticated industry, there are still great opportunities to realize major efficiencies by wisely applying advanced analytics and data engineering. All business processes in logistics rely on accurate demand forecasting in the short, medium, and long-term to inform resourcing, planning, and staffing to support future needs. Our client was three months into a highly-visible, strategic analytics project and with an urgent need to integrate forecast results in their production system. For this major multi-national logistics organization, failure to deploy to production would mean huge losses in both development costs, person-hours, and opportunity cost in future demand forecasting gains. Given the strategic importance of this project, they needed to quickly scale a forecast model into their automated production system that interfaced with a new platform for their planners. Elder Research successfully implemented and integrated the automated framework for time-series forecasting.
Elder Research provided a bridge between technical experts and the application development team responsible for time-series forecast implementation. Our team of experts worked collaboratively with the prototype model authors, software developers and architects, database administrators, and business stakeholders to ensure that our production solution would meet their requirements, interface with existing systems, and provide the flexibility required for future development. We also provided a valued perspective on statistical and optimization techniques for the operations research team that created the model.
The strength of our approach came from our multidisciplinary team and approach. We not only understood the data science and analytics behind the model, but were able to successfully communicate with the engineering and IT teams as well as the business stakeholders to create and execute a successful path to production deployment.
Within three weeks, our team delivered a functioning production time-series forecasting framework. Within six months, our team scaled the framework to produce 35 million forecasts on over 2000 locations in under one hour of computation time. This framework features automated execution and algorithm selection at short, medium, and long-term horizons. At a two-week interval, our forecasts had a median accuracy of 88%, despite high variance in the characteristics of the entities being forecast. We also developed a flexible forecasting model API to enable easy inclusion/exclusion of time-series algorithms as better techniques are identified or existing algorithms are replaced.
Our client was incredibly pleased with the results- not only our team’s ability to deliver a high quality framework in such a short amount of time, but also our team’s ability to navigate the various organizational hurdles and constraints to successfully deliver. The framework and output has continued to help this major logistics organization’s ongoing maturity in automated demand forecasting, leading to multi-million-dollar savings.