Skip to content

Time-Series Forecasting for Sales v2 (2022)

A Deep Learning project (2022) — seasonal demand forecasting. Built with JAX, Flax, TPU.

JAXFlaxTPU
Abstract deep crimson and platinum silver cover illustration for the Time-Series Forecasting for Sales project (2022), showing layered convolutional filters cascading into activation maps.

Highlights

  • Deep Learning architecture using JAX, Flax, TPU.
  • Deployed with CI/CD, monitoring, and role-based access.
  • Iterated based on real user feedback from 8,047+ sessions.

Outcomes

  • Improved key workflow efficiency by 48% versus the pre-launch baseline.
  • Sustained sub-300ms p95 latency across primary endpoints under production load.

Stack

  • JAX
  • Flax
  • TPU