Internet-of-Things sample application: Connected pinball machine

Expert: Michael Scharpf

Industry: Other

Area: Marketing & Sales

A pinball machine from the 80s becomes a networked high-tech device: Find out how our Connected Pinball became a unique example project thanks to the Internet of Things and Machine Learning.



In our internal project, we had a special challenge: to network an old, ur-analogue product, a pinball machine from 1987, with modern technology and thus make the concept of the Internet of Things (IoT) tangible. The goal was to collect data and develop predictive models for the game.


To overcome the challenge, we opted for a solution based on the use of Raspberry Pis, camera and machine learning algorithms. By using two Raspberry Pis, the pinball machine could be networked with various sensors and actuators to collect data in real time. A camera was added to capture unstructured image data showing the current game state. Machine learning was then used to develop predictive models and create customised D3 visualisations to analyse and display game play.


The result was impressive: the game on the pinball machine was visualised in real time on two monitors and a pattern recognition system identified the current score based on the recorded image data. This gave the team a new opportunity to explore the Internet of Things with modern technology and to apply data analysis methods. The project illustrates how artificial intelligence and machine learning can be used to develop innovative applications even on supposedly old-fashioned devices.

To implement the project, we used Python as the programming language and TensorFlow as the machine learning framework. The combination of these technologies allowed us to effectively process the pinball machine data and develop predictive models.

Overall, the project shows how innovative technologies such as IoT and Artificial Intelligence can be used to open up new possibilities for data analysis and support companies in their growth.

This example shows how the concept of the Internet of Things can be made tangible through collaboration with our company. The combination of Raspberry Pis, Machine Learning algorithms and D3 visualisations allowed us to develop predictive models and collect data in real time. The result is an innovative application that shows how Artificial Intelligence and Machine Learning can be used on old devices like a pinball machine.

Curious now? Let us show you what sets us apart from other companies and how we can help you achieve your goals.

Michael Scharpf - Key Account Manager

Your expert

Michael Scharpf | Sr. Principal Key Account Manager | Alexander Thamm GmbH