Titouan Jehl, PhD

Titouan Jehl, PhD

Data Scientist

Lyft, Inc

About me

I am Data Scientist at the ride-sharing company Lyft where I conduct research on dispatch algorithms. I graduated in 2020 from UC Berkeley with a PhD in Industrial Engineering and Operations Research. My advisor was Professor Max Z. Shen. I have also completed a MSc degree in Artificial Intelligence from Ecole Polytechnique (Computer Science)

Previously I worked as a Data Scientist for the e-retailer JD.com and the consulting firm BCG.

Interests

  • Discrete Optimization
  • Routing & Logistics
  • Algorithms
  • Machine Learning
  • Artificial Intelligence

Education

  • PhD in Industrial Engineering & Operations Research, 2020

    UC Berkeley

  • MSc in Computer Science, 2016

    Ecole Polytechnique

  • BSc in Engineering, 2014

    Ecole Polytechnique

Experience

 
 
 
 
 

Research Scientist

Lyft

May 2019 – Present California
  • Implemented a new dispatch policy for shared riders that optimizes the trade-off between passenger waiting time and marketplace efficiency.
  • Implemented a model to guide the decision of launching a ride sharing service in a new city.
 
 
 
 
 

Research Scientist

JD.com

May 2018 – Dec 2018 California
  • Developed an algorithm for inventory placement in a network of warehouses. This algorithm will save hundreds of millions of orders from being delayed each year.
  • Designed a policy and an algorithm to handle the replenishment of connected vending machines.

Recent Posts

A Sequential Decision-Making Process for Smart Vending Machine Replenishment Systems

Vending machines provide people with an easily accessible selection of beverages and snacks, helping them to quickly quiet their rumbling stomachs while on the go. However, vending machines can pose frustrations from time to time — coins or bills being rejected, purchased items getting stuck in the machine, products being out-of-stock, and more.

Solving Inventory Assortment Problem Using Parametric Cuts

For JD.com, shipping as fast as possible is key to satisfying customers. JD.com is proud to be able to deliver over 90% of its packages in the same or next day.

Recent & Upcoming Talks

Shared Ride Sustainability

E-hailing companies offer classic rides as a fast mode of transportation and shared ride as an economy option. Unlike private riders, …

Product Placement Optimization Using Parametric Cuts

E-Commerce companies use forward distribution centers (FDC) that are closer to customers distance-wise to fulfill orders in a timely …

Data Science in Retail-as-a-Service

E-commerce has been growing exponentially during the last couple of centuries around the world due to expanding access to the Internet and, more recently, mobile technology. The ability to shop online has transformed how consumers interact with brands and retailers, and how global commerce operates. Recently, more and more companies, including those with strong focuses on technology and AI, are promoting Retail-as-a-Service (RaaS) as a solution to offer customers more intimate and personalized shopping experience. This is achieved by creating a boundaryless shopping experience where customers, goods and shopping environments are more tightly integrated. Data mining and data science are among the core techniques in RaaS. In this tutorial, we will provide an overview of the current best practices of RaaS, and highlight the key contributions that data science has made in the field. We will use real world application examples to demonstrate how data science has changed the shopping experience both online and offline ,and what the future of shopping might be.

Contact