Great work team!
The most difficult part of this challenge is to understand the data, create new features and rerun the predictive models till you achieve a good accuracy.
As you may mentioned if you run a predictive model with the initial dataset you will get an extremely low modelling accuracy.
I will vote based on the below criteria:
1. business understanding
2. feature engineering
3. modelling accuracy
4. insights & final results
You achieved a fair but not great modeling accuracy and you created a number of new features based on your good understanding of the data and the business case.
You could increase the accuracy of the model by implementing a base price algorithm and then by taking the % of difference between the actual and the base price you could extract the weekly promotional price reduction and use it as input parameters for your regression model. This was your pain point on a very nice job
Congratulations to team 31415 for taking up a difficult challenge primarily because, as some might say, the data size for this problem was very small. However, the best part was that problem was well defined.
I thoroughly enjoyed reading a very crisp flow of ideas and implementation on the case. I liked that the team though of using multiple algorithms but discounted that because of limitations of the algorithm given the data.
The only suggestion Iβll like to provide is that the team should have thought twice on using train_test_split at (80,20). Typically when the observations are so less (especially in the medial research studies) the choice is one-vs-all or leave-one-out. However, neither of those methods could have guaranteed a significant change in the model response.
Best of luck.
Hi team! In brief: I like your different approach for analysis, ideas for derived variables and also appreciate the comparison of diff. modelling techniques. π
Would be happy to see continuation of your work here.
3 thoughts on “CASE SAP, TEAM 31415”
Great work team!
The most difficult part of this challenge is to understand the data, create new features and rerun the predictive models till you achieve a good accuracy.
As you may mentioned if you run a predictive model with the initial dataset you will get an extremely low modelling accuracy.
I will vote based on the below criteria:
1. business understanding
2. feature engineering
3. modelling accuracy
4. insights & final results
You achieved a fair but not great modeling accuracy and you created a number of new features based on your good understanding of the data and the business case.
You could increase the accuracy of the model by implementing a base price algorithm and then by taking the % of difference between the actual and the base price you could extract the weekly promotional price reduction and use it as input parameters for your regression model. This was your pain point on a very nice job
Congratulations to team 31415 for taking up a difficult challenge primarily because, as some might say, the data size for this problem was very small. However, the best part was that problem was well defined.
I thoroughly enjoyed reading a very crisp flow of ideas and implementation on the case. I liked that the team though of using multiple algorithms but discounted that because of limitations of the algorithm given the data.
The only suggestion Iβll like to provide is that the team should have thought twice on using train_test_split at (80,20). Typically when the observations are so less (especially in the medial research studies) the choice is one-vs-all or leave-one-out. However, neither of those methods could have guaranteed a significant change in the model response.
Best of luck.
Hi team! In brief: I like your different approach for analysis, ideas for derived variables and also appreciate the comparison of diff. modelling techniques. π
Would be happy to see continuation of your work here.