The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Gradient boosting weights analysis
k_vishnu772
Member Posts: 34 Learner III
HI All,
i am working on a small data set of 250 rows and 17 features from chemical industry and expert people would like to know the most infuential parameters for the target based on the given data.
I got the weights from Gradient boosting algorithm but,i would like to know is this weights true ? with what confidence i can trust these weights? According to the experts there is one feature which was given low weigth which they think that should be given high weight .
could you please help me how can i trust my weights from gradient boosting.
Regards,
Vishnu
Tagged:
0
Answers
Trusting your model is why you conduct validations. It is not uncommon for a machine learning algorithm to come up with a solution that doesn't correspond to expert intuition.
You can also try building a model with and without the attribute in question to see whether it has much impact on the results.
Lindon Ventures
Data Science Consulting from Certified RapidMiner Experts