Mini series: How to implement your ESG reporting
Part 1 of 2: Introduction & Reporting
Data alone is only a collection of measurements and counts. Only their analysis creates meaningful findings.
In this fast-growing field, new methods for improving knowledge acquisition are being developed daily. If these methods are applied, a better understanding of one's own company often emerges. You profit from this in the long term.
Companies often have a rich data situation without knowing what added value can be achieved with it. This is where we as a team start with our "Vision Workshop" model.
We offer you a free workshop via video conference to discuss your data and its possibilities - completely free of charge.
Viewing relevant data and working out a
Target image and highlighting added value for the company
In this step we take care of the data preparation
the data sources relevant and underlying the project
Analysis of results using the latest methods from the fields of "Supervised and Unsupervised Learning," "Deep Learning," or Neural Networks.
Visual processing of the results and Productization in existing or new infrastructure
Julian Spöri is Senior Consultant and Team Lead of the Data Science department at M2. In his many years of experience as a Data Science & Data Engineering Consultant, he has already managed various customer projects with a wide range of requirements.
Together with his team, he will also be happy to advise you in order to find an optimal solution for your requirements!
Data Science Lead
Part Default Probability & Life Expectancy
A service provider for the automotive industry would like to use machine learning algorithms for the prediction and inspection of quality problems on the one hand, and on the other hand also use the possibilities of an interactive Data analysis. The interactive data analysis is intended to enable end users from the various departments to quickly and precisely analyze the data and verify the results of the ML algorithms.
In this project a machine learning application in Python was developed, which predicts the life expectancy of individual parts based on more than 100 variables. An interactive Tableau dashboard solution with over 20 individual dashboards, including complex user navigation, was developed to make the data visually consumable.