Content clustering using word2vec
Honeyscreen, a key product of Buzzvil, serves not only ads which give reward point to users, but also various content. Users can see breaking news and hot content in their lock scr…
Data & machine learning
How we move data, make predictions and learn from real systems.
Start here
More in this topic
Browse all 25 piecesImproving CI Tests for Airflow Data Pipelines
How cache isolation, dependency changes, reusable Airflow setup, and parallel execution cut data pipeline CI time roughly in half.
Buzzflow, Buzzvil’s ML Platform (1): Developing and Managing Models
How Buzzflow standardizes model pipelines, local debugging, registries, permissions, and monitoring around SageMaker and MLflow.
Building a Self-Service Data Platform with Airflow
How YAML templates and a DAG factory let teams create reliable data pipelines without depending on data engineers for every request.
Building a Scalable Ad Server with Elasticsearch
The ad server is a core component of Buzzvil’s rewarded advertising platform. One of its main jobs is targeting: delivering ads to users who match the criteria advertisers specify.…
Optimizing Item-CF for Product Recommendations
Buzzvil serves 30 e-commerce advertisers. To improve our retargeting solution, we introduced the Item-CF product recommendation algorithm. Here is how we optimized and deployed it.…
Applying Probabilities in Elasticsearch Searches
This post explains two effective ways to apply probabilities to individual documents in Elasticsearch searches, with a brief performance comparison and discussion of their tradeoff…
Minerva: Airbnb's Metric Platform
On June 3, 2022, data engineer Raf shared a presentation on Minerva, Airbnb’s metrics platform at Buzzvil Tech Weekly. See the slides below for more details.
Buzzvil Billing Data Pipeline
In the first week of February 2022, server developer Will presented Buzzvil Billing Data Pipeline, explaining how Buzzvil’s billing data is produced at Buzzvil Tech Weekly. See the…