You can try out some demos of machine learning models for real life problems that often crop up in industry. The models are examples and not intended for production use.

• Author prediction demo – a demo of a Convolutional Neural Network used for Forensic Stylometry, i.e. identifiying who wrote a document out of a set of known authors.
• Machine learning model predicting vessel detentions – a model in Microsoft Azure ML predicting which vessels in port of Singapore are likely to be detained by port authorities, using live data feed of ships’ movements.
• Customer churn demo – a machine learning model predicting the likelihood of a customer ending a utility contract.
• Motion classification demo – a model that classifies accelerometer readings into actions such as walking, falling or sitting.