Model Training

Assessment of model

In this lesson, we will explore the standard process for gathering data to train a model and tune hyperparameters optimally to achieve a certain level of performance and optimization. In the implementation phase—step four of the NPD process—we’re looking for a level of performance that would be considered optimal based on the define phase—step two of the NPD process—before we move to the next phase of marketing and crafting our message for what success looks like when using our product. A lot has to happen in the implementation phase before we can do that.

Data accessibility

Data accessibility is the most important factor when it comes to AI/ML products. At first, we might have to start with third-party data, which we’ll have to purchase, or public data that are freely available or easily scraped. This is why we’ll likely want or need to partner with a few potential customers. Partnering with customers we can trust to stick with us and help us build a product that can be successful with real-world data is crucial to ending up with a product that’s ready for market. The last thing we want is to create a product based on pristine third-party datasets or free ones that then become overfitted to real-world data and perform poorly with data coming from our real customers that it’s never seen before.