Skip to content
This repository contains some basic instructions given during the IT Meetup Opole#2 as a preparation for HACKATHON DANONE AI MASTERS OPOLE 2019
Branch: master
Clone or download
Latest commit e004fce Apr 13, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Hackathon utils Update README.md Apr 13, 2019
IT Meetup Opole #2 - Machine Learning troubleshooting images in Notebooks Mar 25, 2019
.gitignore Initial commit Mar 18, 2019
LICENSE Initial commit Mar 18, 2019
README.md Update README.md Mar 20, 2019
nohup.out troubleshooting images in Notebooks Mar 25, 2019

README.md

This repository will be used as code and instructions source for the HACKATHON DANONE AI MASTERS OPOLE 2019.

A pre-hackathon Meetup, IT Meetup Opole#2, is organised on March 21st, 2019. All the information shared during this event is posted here containing some basic instructions on how the data was prepared and a full description of the industrial processes followed during the baby-food production

More information about the events can be consulted here


Repository introduction

The data explained here represents the historical data from several years of baby-food production. Different recipes are under consideration. This data is being released as a challenge for the HACKATHON DANONE AI MASTERS OPOLE 2019, MACHINE LEARNING CHALLENGE.

As part of the digitalisation efforts and implementation of I4.0 best practices, Danone Opole starts its data-journey by preparing historical data comprising the orders, characteristics of the raw materials used on each recipe, variables used during the food-processing and different variables measured from the semi-finished product.

Challenge

The challenge, if you decide to accept it! is to build a model that will allow estimating the food-processing parameters that will provide the expected parameters in the semi-finished products

Mentoring during the events

I have been tasked to support the Danone Opole team in the preparation of the data and further mentoring during the events.

To introduce the participants to the Hackathon's challenge, I am sharing the process of preparing the data from the existing sources to a more useful format. Extraordinary efforts were made to create a robust data model and remove, as much as possible, inconsistencies and errors introduced during the digitisation of the paper-based data and further match to available digital data sources.

If you would like to get in touch please visit my LinkedIn profile

You can’t perform that action at this time.