With the growing popularity of online shopping, e-commerce, and instant grocery shopping, there’s a growing necessity for an algorithm that can identify products in our inventory that are similar to those offered by competitors.
Ensuring feature quality is crucial for the performance of ML models. Leveraging our experience at Delivery Hero, we’ve developed components that integrate with our Feature Store to tackle data issues. This article will explore the processes for maintaining feature quality, as well as the advantages gained through effective feature monitoring.
Previous blog posts have discussed capturing new customers onto our platform, but that’s one step along the customer journey. We aim to retain these customers and deliver to them the best delivery experience imaginable.
At Delivery Hero, data science and machine learning play an essential role in personalizing the experience of our users. To enhance the efficiency of the feature engineering process, the ML Platform team has designed and developed a Feature Store solution that empowers data scientists to efficiently create, monitor and serve features for their machine learning models.
As it is said “First impression is the last impression”, providing tailored recommendations to new users goes a long way in the retention journey and maintains stickiness to the platform.
How fast and accurately do the top three gradient-boosting algorithm implementations in ML perform on prediction tasks? In this study, we conducted a head-to-head analysis of CatBoost, LightGBM, and XGBoost, utilising an openly accessible WEB10K dataset and uncovered fascinating insights.