Alex Rodin

Alex Rodin

Alex Rodin has over 18 years of experience in programming and software development, graduating from Saratov State University with a degree in Applied Mathematics in 2001. He then taught at Saratov for 10 years as a member of the Computer Sciences and Information Technologies faculty. Alex joined Grid Dynamics in 2009 as an Architect and Senior Staff Engineer and has been with the company ever since. He is currently a Principal Software Engineer working on Machine Learning at Grid Dynamics Labs, our innovation center.

Alex Rodin

Alex Rodin has over 18 years of experience in programming and software development, graduating from Saratov State University with a degree in Applied Mathematics in 2001. He then taught at Saratov for 10 years as a member of the Computer Sciences and Information Technologies faculty. Alex joined Grid Dynamics in 2009 as an Architect and Senior Staff Engineer and has been with the company ever since. He is currently a Principal Software Engineer working on Machine Learning at Grid Dynamics Labs, our innovation center.

Alex Rodin

Unsupervised real time anomaly detection

This article presents a solution for real-time anomaly detection using component metrics aggregated in time series. The solution evolves from deep learning models to gradient boosting models to neocortex neural networks, providing real-time data ingestion, training, and detection, as well as the ability to onboard new metrics and detect anomalies in a continuous time frame.

Safety stock optimization for ship-from-store

Retailers are constantly looking for ways to improve the speed of delivery in online retail. One way to achieve this is by implementing options such as Buy Online Pick Up in Store (BOPUS) and Ship from Store (SFS). However, these options bring about challenges in terms of inventory reservation. This article discusses the inventory optimization problem for BOPUS and SFS and provides a case study on how machine learning methods can be used to solve this problem.