Summary

In this chapter, we have explored how insights can be generated from an image, location, and free text. In so doing, we highlighted the benefits that these data types present, as well as the challenges that come with each of them. We also pointed out how these are typically addressed in the mainstream. We proceeded to build models with a multimodal dataset using DataRobot and make predictions from the model. We also looked at a variety of ways to derive insights from the location, free text, and image aspects of the models. By demonstrating the process of model building using a multimodal dataset, we showed how DataRobot simplifies the handling of the challenges different data types pose.

Having said that, it is important to draw attention to the fact that DataRobot appears to have some limitations in terms of free text processing. Whilst the platform significantly simplifies the process of text processes, at the time of this publication, we are unsure of the extent to...