Machine Learning Projects for Mobile Applications

Building your own model

With the knowledge that you gained from this book, you can start to develop your own model that runs on a mobile phone. You will need to identify the problem statement first. There are many use cases where you will not need an ML model; we can't unnecessarily force ML into everything. Consequently, you need to follow a step-by-step approach before you build your own model:

1. Identify the problem.
2. Plan the effectiveness of your model; decide whether the data could be useful in predicting output for future, similar cases. For example, collecting the purchase history for people of a similar age, gender, and location would be helpful in predicting a new customer's purchase preferences. However, the data wouldn't be helpful ...