Onedot uses advanced artificial intelligence and machine learning algorithms to independently learn from both data and user feedback.
When users upload data, Onedot statistically analyses the data, looks for patterns and practices used in the particular data sets. This includes learning the target data schema being used in the database, such as a Product Information Management (PIM) system, an Enterprise Resource Planning (ERP) system or a shop system, as well as types and ranges of values to expect, product categories, product variants, localisation preferences, formatting preferences, etc. This is called unsupervised learning.
Users can also give feedback to the decisions taken by Onedot. This can include decisions such as identifying duplicate records, joining columns of different data sets, or matching records between different data sets. Onedot captures this feedback from the user, usually a business expert, in the form of simple yes/no questions. The feedback is used internally by Onedot to train the artificial intelligence algorithms and statistical models to become better and stronger over time.
Related articles
| Filter by label (Content by label) |
|---|
| showLabels | false |
|---|
| max | 5 |
|---|
| spaces | WP |
|---|
| showSpace | false |
|---|
| sort | modified |
|---|
| reverse | true |
|---|
| type | page |
|---|
| cql | label in ( "learning" , "machinelearning" , "faq" ) and type = "page" and space = "WP" |
|---|
| labels | machinelearning learning faq |
|---|
|