by Alexander Reiss
how machine learning optimizes the management of a branch network
Automotive companies, fast food chains or any company operating a large branch network – especially at international level - all face the same challenge: how to manage these networks as efficiently and impartially as possible. We give answers on how artificial intelligence may be the solution.
most frequent questions on machine learning
what role do key performance indicators play?
The Management Board uses this data to assess performance of individual branches and devise subsequent strategic measures. The process of reading, aggregating and visually processing the data takes an enormous amount of time, but is necessary to present the results to the Management Board.
why is an intelligent automation of this process necessary?
Valuable management work time can be released with a manageable project effort. If the company operates a network of 5,000 branches without an automation process, the board needs 125,000 minutes of management time per control cycle. This corresponds to 2,083 working hours – more than the entire annual working time of an employee working a 40-hour week!
how can we simplify the control process through artificial intelligence?
An AI-based application can recommend or dismiss strategic measures on the basis of the KPIs, and different methods within machine learning such as logistic regression, k-nearest neighbors, neural networks, or support vector machines can be applied. Ideally, this data should have been compiled correctly and without any gaps, as each model can only be trained as good as the underlying data allows.
how does the model support the Management Board?
If the model’s performance based on unknown data is good enough, the model has "learned" which strategic measures can be derived from certain combinations of KPIs. In the next step, the model is "fed" current KPI data. This allows calculation of the appropriate strategic measures, which are then submitted to the Management Board to aid decision-making.
that means, the model can "learn"?
It can be improved after each control cycle. The final strategic measures taken are used to further train the model. This means continuous improvement of the algorithm’s performance.
what potential offers machine learning for companies?
Since supervised learning systems can only handle information previously taught, the control process will need human assistance in new situations. Apart from that, a machine that has undergone sufficient training can actually perform standard control processes autonomously, which promises great potential for companies. The data already exists, now it is important to use it in the desired correlation.
The complete article is also published on LinkedIn.