MediaRadar | Vivvix uses GenAI and computer vision on Databricks to automate video ad classification
MediaRadar | Vivvix built a GenAI pipeline on Databricks using Spark Structured Streaming, the Ray cluster, Whisper for transcription/translation and OCR to classify video ads across millions of product categories. A dual-layer approach combines GenAI product identification with in-house classification models, increasing hourly ad-classification throughput from about 800 to 2,000 creatives and cutting model-experimentation time from two days to half a day.
Overview
MediaRadar | Vivvix built a GenAI pipeline on Databricks using Spark Structured Streaming, the Ray cluster, Whisper for transcription/translation and OCR to classify video ads across millions of product categories. A dual-layer approach combines GenAI product identification with in-house classification models, increasing hourly ad-classification throughput from about 800 to 2,000 creatives and cutting model-experimentation time from two days to half a day.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
MediaRadar | Vivvix faced manual data processing and fragmented workflows that couldn't keep pace with rapidly growing ad volumes. Their prior Amazon SQS setup, limited to manual polling of 10 messages at a time, hindered SLA compliance, and classifying over 6 million unique products was an extreme classification problem that existing in-house ML models and hundreds of human operators manually watching ads could not scale to match nearly doubling ad spend.
The solution
MediaRadar | Vivvix adopted Databricks and Apache Spark Structured Streaming for automated, continuous real-time data ingestion, using a Ray cluster on Databricks to scale video-ad classification. A dual-layer approach uses GenAI to identify products in ads and compares results with in-house classification models to select the best match. Preprocessing pipelines include fingerprinting for duplicate detection, Whisper for transcription/translation, and OCR for text extraction, with Databricks Model Serving used for rapid prototyping and OpenAI's GPT-3.5 chosen to balance performance and cost; the team is also moving to Databricks Unity Catalog for governance.
Reported business value
MediaRadar | Vivvix increased ad classification throughput from about 800 to roughly 2,000 creatives an hour, a 150% increase in ads categorized per hour, while model experimentation and testing time that used to take about two days now takes as little as four hours, and moving into Databricks eliminated the data silos and fragmented pod monitoring that previously made operations hard to track.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other technology & software entries in the register.
HP crafts marketing campaigns that resonate with customers using Databricks and Uniphore
HP centralized first-party customer data on the Databricks Data + AI Platform with Delta Lake and Unity Catalog, and connected it to Uniphore's HybridCompute for federated query pushdown, cutting campaign setup from 2 weeks to 2 hours and processing 400 million records in seconds.
Building a safer and more sustainable world
Novade, a construction management software company, partnered with Databricks to modernize its analytics and ML infrastructure, moving from a homegrown Apache Airflow stack to the Databricks Data + AI Platform with Delta Lake, Unity Catalog and MLflow. The move reduced total cost of ownership by 60% and supported a 100% increase in new clients, while enabling ML models for predicting incident risk affecting worker safety and project delivery schedules.
SafeGraph optimizes geospatial data processing with Databricks and Delta Sharing
SafeGraph used the Databricks Data + AI Platform, Delta Lake, Delta Sharing and MLflow to process petabytes of geospatial data and feed predictive models, achieving 2x-10x faster spatial querying, indexing and partitioning and a 50% reduction in peak memory consumption compared to other platforms, while reducing data access time for partners from months to minutes via Delta Sharing.
Transforming Weather Forecasting with Lakeflow Jobs
AccuWeather migrated from on-premises infrastructure to Databricks and Lakeflow Jobs, working with Datadog for observability, to unify diverse weather data formats and orchestrate 4,500+ weekly jobs. Lakeflow Jobs coordinates the ingestion of multiple weather models, triggers machine learning processes that weight and blend different forecasts, and manages complex job dependencies for reinforcement training workflows used in AccuWeather's proprietary forecasting engine. AccuWeather reports 3x faster dataset development (three months to one month per dataset), a 50% reduction in unactionable alerts, and 50% cost savings on serverless job usage.
AccuWeatherLakeflow Jobs · Delta Sharing · DatadogWas this helpful?
Your feedback helps us improve our use case database