Need for Data-centric ML Platforms
This blog is the first in a series on MLOps and Model Governance. The next blog will be by Joseph Bradley and will...
How to Build a Scalable Wide and Deep Product Recommender
Download the notebooks referenced throughout this article. I have a favorite coffee shop I've been visiting for years. When I walk in, the...
Machine Learning-based Item Matching for Retailers and Brands
Item matching is a core function in online marketplaces. To ensure an optimized customer experience, retailers compare new and updated product information against...
How Outreach Productionizes PyTorch-based Hugging Face Transformers for NLP
This is a guest blog from the data team at Outreach.io . We thank co-authors Andrew Brooks, staff data scientist (NLP), Yong-Gang Cao...
Improving Customer Experience With Transaction Enrichment
The retail banking landscape has dramatically changed over the past five years with the accessibility of open banking applications, mainstream adoption of Neobanks...
Building Forward-Looking Intelligence With External Data
This post was written in collaboration with the Foursquare data team. We thank co-author Javier Soliz, sales engineer specializing in data engineering and...
Data-driven Software: Towards the Future of Programming in Data Science
This is a guest authored post by Tim Hunter , data scientist, and Rocío Ventura Abreu , data scientist, of ABN AMRO Bank...
Reproduce Anything: Machine Learning Meets Data Lakehouse
Machine learning has proved to add unprecedented value to organization and projects - whether that’s for accelerating innovation, personalization, demand forecasting and countless...
How (Not) to Tune Your Model With Hyperopt
Hyperopt is a powerful tool for tuning ML models with Apache Spark. Read on to learn how to define and execute (and debug)...
Fine-Grained Time Series Forecasting at Scale With Facebook Prophet and Apache Spark: Updated for Spark 3
Advances in time series forecasting are enabling retailers to generate more reliable demand forecasts. The challenge now is to produce these forecasts in...