<- Back to Events

Webinar: Advanced time-series Machine Learning inside MariaDB

12

MindsDB and MariaDB co-hosted a live webinar on May 18th at 4PM GMT on Advanced time-series Machine Learning inside MariaDB.

Our speakers showcased how by using SQL and the innovative technology called AI Tables you can apply machine learning models directly in MariaDB to generate forecasts as simple tables.

Databases is where most data is stored. Databases are also very good at manipulating data, and yet data scientists spend most of their time (80% according to a Forbes study) collecting and cleaning data using tools outside of the database. Why not bring it all together?

MindsDB and MariaDB have built an integration that makes machine learning possible from inside the database using plain SQL.

How? This is where "AI Tables" come in. They can help simplify building, training, and querying ML models, using nothing but SQL. They also come with the added benefit of simplifying applications and reducing the amount of ETL needed!

In the journey of bringing AI Tables to MariaDB, we have also discovered and solved Machine Learning problems that are hard even for ML engineers but become very simple inside databases.

One of such problems is multivariate time-series forecasting.

For example, forecasting inventory for all products in all stores (GROUP BY store, product_id), given a table that contains all inventory updates over time (ORDER BY time).

This problem is hard even for the most experienced ML engineering teams. In a traditional ML approach, you would need to train one model for each product at each store, which can mean thousands or hundreds of thousands of models not even thinking of the logistic nightmare to bring such many models to production.

We have made incredible progress in solving those problems through AI-Tables and we would like to share with you our solutions and discuss some interesting ideas that have occurred in the process.

<- Back to Events

ON-DEMAND WEBINAR​

Advanced time-series Machine Learning inside MariaDB


SPEAKERS

Vicentiu Ciorbaru, Team Lead,  MariaDB Foundation

Jorge Torres, CEO, MindsDB

Patricio Cerda-Mardini, AI Research, MindsDB


SPECIAL GUEST​

Michael Widenius, Chief Server Architect, MariaDB Corporation

12

MindsDB and MariaDB co-hosted a live webinar on May 18th at 4PM GMT on Advanced time-series Machine Learning inside MariaDB.

Our speakers showcased how by using SQL and the innovative technology called AI Tables you can apply machine learning models directly in MariaDB to generate forecasts as simple tables.

Databases is where most data is stored. Databases are also very good at manipulating data, and yet data scientists spend most of their time (80% according to a Forbes study) collecting and cleaning data using tools outside of the database. Why not bring it all together?

MindsDB and MariaDB have built an integration that makes machine learning possible from inside the database using plain SQL.

How? This is where "AI Tables" come in. They can help simplify building, training, and querying ML models, using nothing but SQL. They also come with the added benefit of simplifying applications and reducing the amount of ETL needed!

In the journey of bringing AI Tables to MariaDB, we have also discovered and solved Machine Learning problems that are hard even for ML engineers but become very simple inside databases.

One of such problems is multivariate time-series forecasting.

For example, forecasting inventory for all products in all stores (GROUP BY store, product_id), given a table that contains all inventory updates over time (ORDER BY time).

This problem is hard even for the most experienced ML engineering teams. In a traditional ML approach, you would need to train one model for each product at each store, which can mean thousands or hundreds of thousands of models not even thinking of the logistic nightmare to bring such many models to production.

We have made incredible progress in solving those problems through AI-Tables and we would like to share with you our solutions and discuss some interesting ideas that have occurred in the process.