OpenTable helps diners find the best dining experiences, wherever they travel. Tastes vary widely between our diners, however, so we need to personalize our recommendations to find restaurants which can provide great dining experiences. Fortunately, we have more than fifteen million unstructured reviews which we can use to build models which improve the accuracy of our recommendations.
Sudeep Das and I presented a talk at Spark Summit 2015 in San Francisco on how we use Spark both for the training of our recommenders, and for the natural language processing of the reviews to generate topic models.
Slides for this talk are available here and you can watch a “Spark Spot” featuring us here.
