13
MindsDB and Altinity co-hosted a live webinar on June 10th, 2021 on machine learning capabilities inside ClickHouse.
Predictive analytics are popular in applications ranging from real-time marketing to factory maintenance. The key challenge is to integrate machine learning with the pools of data required to train models. In this webinar we will show how to operate machine learning models from within ClickHouse using MindsDB.
The webinar starts with an overview of MindsDB, showing how it integrates easily with SQL using AI tables. Next, we’ll show best practices for ClickHouse queries to ingest training data into MindsDB, as well as to invoke models on new data. Finally, we’ll show a demonstration of multivariate time-series forecasting on the popular New York Taxi and Limousine Commission dataset.
Imagine you have a table with inventory changes over time of multiple products across multiple sores, and you want to forecast this inventory. In a classical machine learning approach, this becomes a tough problem. You have to train one model for each product at each store, meaning having thousands of models, not even thinking of the logistic nightmare to bring so many models to production.
But AI Tables solve this for you so that you can build just one single model instead of thousands. In this webinar, we would like to share how easy it is to use machine learning inside ClickHouse and demonstrate how unique forecasting capabilities over multivariate time-series data works.
MindsDB and Altinity co-hosted a live webinar on June 10th, 2021 on machine learning capabilities inside ClickHouse.
Predictive analytics are popular in applications ranging from real-time marketing to factory maintenance. The key challenge is to integrate machine learning with the pools of data required to train models. In this webinar we will show how to operate machine learning models from within ClickHouse using MindsDB.
The webinar starts with an overview of MindsDB, showing how it integrates easily with SQL using AI tables. Next, we’ll show best practices for ClickHouse queries to ingest training data into MindsDB, as well as to invoke models on new data. Finally, we’ll show a demonstration of multivariate time-series forecasting on the popular New York Taxi and Limousine Commission dataset.
Imagine you have a table with inventory changes over time of multiple products across multiple sores, and you want to forecast this inventory. In a classical machine learning approach, this becomes a tough problem. You have to train one model for each product at each store, meaning having thousands of models, not even thinking of the logistic nightmare to bring so many models to production.
But AI Tables solve this for you so that you can build just one single model instead of thousands. In this webinar, we would like to share how easy it is to use machine learning inside ClickHouse and demonstrate how unique forecasting capabilities over multivariate time-series data works.
.png)
.png)
