cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 
Help
User16857281869
New Contributor II
since ‎08-21-2021
‎06-26-2023

User Stats

  • 5 Posts
  • 0 Solutions
  • 0 Kudos given
  • 1 Kudos received

User Activity

What are the best ways of developing a customer churn usecase on databricks?

06-18-2021
In this blog we implement a typical model for customer attrition in subscription models from data preparation to operationalisation of the model.

We want to do demand forecasting for our supply chain. How should we benefit from Spark in the Usercase development?

06-18-2021
We have a series of blogs on the topic which describe the challenges and the best practices on development of demand forecasting usecases on Databricks. Please refer to this blog and the references in it for more info.

What is the best way to do time series analysis and forecasting with Spark?

06-18-2021
We have developed a library on spark which makes typical operations on time series much simpler. You can check the repo in Github for more info. You could also check out one of our blogs which demos an implementation of a forecasting usecase with S...

Why do I see a cost explosion in my blob storage account (DBFS storage, blob storage, ...) for my structures streaming job?

06-18-2021
Its usually one or more of the following reasons:1) If you are streaming into a table, you should be using .Trigger option to specify the frequency of checkpointing. Otherwise, the job will call the storage API every 10ms to log the transaction data...

How do I benefit from parallelisation when doing machine learning?

06-17-2021
There are in principle four distinct ways of using parallelisation when doing machine learning. Any combination of these can speed up the whole pipeline significantly.1) Using spark distributed processing in feature engineering 2) When the data set...
Kudos from
View all