You are viewing content from a past/completed QCon

Presentation: Machine Learning: Predicting Demand in Fashion

Track: ML in Action

Location: Cyril Magnin III

Duration: 2:25pm - 2:35pm

Day of week: Tuesday

Share this on:

Abstract

Apparel/fashion retailers often have to buy inventory more than a quarter in advance and so have to make bets on the total demand that they expect to see in the relevant season. Also, the set of products offered by the brands change every year, and even the historical demand for previous season’s products is known only partially as each product is carried in only a subset of the stores.
In this talk, we will show how we (at Celect) use the historical data (point of sales transaction, inventory, product attributes, product images, product descriptions) to build a SaaS solution that helps buyers and merchants predict the future demand of products for the upcoming season. The short talk will cover the real life problem statement, high level ML frameworks, and how the product is used by buyers and merchants.

Speaker: Ritesh Madan

VP Engineering @celect

Ritesh leads the Engineering team at Celect. His team is responsible for building the pDB (predictive Database) platform that provides a database like abstraction to enable predictive queries and machine learning at scale. The pDB platform powers Celect's predictive analytic applications across the two main verticals at Celect: omni-channel retail and federal intelligence. Prior to Celect, Ritesh has led enterprise grade wireless networking products at Cisco, Accelera (now PlumeWifi), and Qualcomm. He has published extensively in optimization, machine learning, and wireless networking, and is a co-inventor on 65 patents. He holds a Ph.D. from Stanford and a BS from IIT Bombay, all in Electrical Engineering.

Find Ritesh Madan at

2019 Tracks

  • Groking Timeseries & Sequential Data

    Techniques, practices, and approaches around time series and sequential data. Expect topics including image recognition, NLP/NLU, preprocess, & crunching of related algorithms.

  • Deep Learning in Practice

    Deep learning use cases around edge computing, deep learning for search, explainability, fairness, and perception.