How did we forecast croissant sales with Catboost?

A data science journey, from notebooks to a deployed product - Part I

Pierre-Yves MOUSSET
Nov 17, 2020 · 12 min read
Photo from https://www.visit.alsace/

TL;DR

Context

Model development

Data request

Exploratory Data Analysis (EDA) and outliers detection

From sales prediction to optimal sales prediction

Our favorite model Catboost

One Catboost vs many Catboost

How to evaluate our ML model?

1. Cross Validation with sklearn

2. The choice of the metric:

Final words, some advice for any data projects

Key Takeaways

Thanks for reading!

Artefact Engineering and Data Science

Dev & Data Science @ Artefact

Artefact Engineering and Data Science

Artefact is a tech company dedicated to solving data challenges by combining state-of-the-art Machine Learning and advanced software engineering. We leverage our business knowledge to deliver tailor-made solutions and bring value to our clients. www.artefact.com @ Artefact

Pierre-Yves MOUSSET

Written by

Senior Data Scientist at Artefact

Artefact Engineering and Data Science

Artefact is a tech company dedicated to solving data challenges by combining state-of-the-art Machine Learning and advanced software engineering. We leverage our business knowledge to deliver tailor-made solutions and bring value to our clients. www.artefact.com @ Artefact