In 1922, physicist Niels Bohr said “making predictions is very difficult, especially about the future”. Making predictions is still difficult. That’s why we delegate the task to computers. By looking for the tiniest, subtlest patterns embedded into masses of data from the past, we can derive the probability of something happening in the future. We give ourselves the best chance of getting it right. Understand how we can “teach” software to make predictions; to draw conclusions; to get to the very meaning of the messy, tangled mass of data that stands before us. That’s the essence of machine learning. This is no longer a project locked within the bowels of Microsoft Research – it’s morphed from impenetrable science into an everyday utility anybody can use on with only a modern web browser We’ll give you practical step-by-step guidance on how to extract learning and expose it as APIs to the Internet. Also how to incorporate them in to your own apps. We’ll show a practical example of building an app that predicts flight delays and another that calls a sentiment analysis API. You’ll walk away from the session with enough knowledge to fire up your first machine learning project