Forecasting algorithms: 3 use cases in food, energy, and transportation
Details
Join us for a deep dive into forecasting! This evening will feature 3 use cases in the food, energy, and transportation industries with guest speakers Irene Iriarte (Data Scientist at Gousto), Will Thomspon (Data Scientist at Veolia), and Alex Combessie (Data Scientist at Dataiku).
Talk 1: Real-time Taxi Fare Prediction by Alex Combessie (Dataiku)
Today, the benefit of Machine Learning is conditioned to its deployment in real-time. In this talk, Alex will explain how to deploy a real-time taxi fare prediction engine to power an Uber-like application. Along the cycle of developing such project, he will highlight key lessons he learned:
- Understand the problem before building models
- Do not add features for the sake of features
- Try as many algorithms as possible
- Simplify your pipeline before deployment
Alexandre Combessie, Data Scientist at Dataiku:
Alex Combessie is a Data Scientist at Dataiku who designs and deploys data projects with Machine Learning from prototype to production. Prior to his time at Dataiku, he helped build the Data Science team of Capgemini Consulting in France. Having begun his career in economic analysis, he continues to work on interpretable models in complement to Deep Learning. Alex is also a travel junkie, who enjoys learning new things and making useful products.
Talk 2: Forecasting Energy Generation by Willi Thompson (Veolia)
Will, Data Scientist at Veolia, will present Veolia's data project to forecast the energy generation at Energy Recovery Facilities (ERF's) across the business. They generate a variable amount of energy depending on several factors, and accurately forecast this generation is paramount in order to maximize value.
Will Thompson, Data Scientist at Veolia:
Will has been a Data Scientist at Veolia for just over 2 years now. Before that, he studied Mathematical Science at the university of Bath. During his time at Veolia, Will has worked on a range of projects such as forecasting energy generation, detecting anomalous behaviour on on-site equipment, and forecasting the rate at which people fill up on-street bins or sites churn.
Talk 3: Gousto's Forecasting Method to Minimise Food Waste by Irene Iriarte (Gousto)
One of Gousto’s main aims is to help our customers minimise food waste while also making home cooking easy. However, we also want to ensure that we are reducing food waste as a business. Our forecasting algorithm plays a crucial part in this and, as part of her talk, Irene will be running through the forecasting method at Gousto and how we have integrated it within the rest of the business.
Irene Iriarte, Data Scientist at Gousto
Irene is a data scientist at recipe kit company Gousto. Since joining in 2016, she has been working on the development of algorithms, focusing on forecasting and personalisation. Before joining Gousto, Irene completed a PhD in computational chemistry at Imperial College London.
Timeline:
6:00 PM: Drinks & networking
6:30 PM: Introduction by Gousto and Dataiku
6:40 PM: "Real-time Taxi Fare Prediction" by Alex Combessie, Data Scientist at Dataiku
7:00 PM: "Forecasting Energy Consumption" by Will Thompson, Data Scientist at Veolia
7:20 PM: Break with pizza & drinks
7:40 PM: "Gousto's Forecasting Method to Minimise Food Waste" by Irene Iriarte, Data Scientist at Gousto
8:00 PM: Drinks & networking
8:30 PM: End of the event
