Using artificial intelligence to design a product
In an embodiment, a method for optimizing computer machine learning includes receiving an optimization goal. The optimization goal is used to search a database of base option candidates (BOC) to identify matching BOCs that at least in part matches the goal. A selection of a selected base option among the matching BOCs is received. Machine learning prediction model(s) are selected based at least in part on the goal to determine prediction values associated with alternative features for the selected base option, where the model(s) were trained using training data to at least identify weight values associated with the alternative features for models. Based on the prediction values, at least a portion of the alternative features is sorted to generate an ordered list. The ordered list is provided for use in manufacturing an alternative version of the selected base option with the alternative feature(s) in the ordered list.
1. A method for optimizing computer machine learning, comprising:
receiving an optimization goal;
using the optimization goal to search a database of base option candidates to identify one or more matching base option candidates that at least in part matches the optimization goal;
receiving a selection of a base option among the one or more matching base option candidates based in part on a ranking of the base option among the one or more matching base option candidates, wherein the base option is scored based in part on a divergence between actual performance that includes measured sales data of the base option and performance that includes expected sales data of the base option predicted by one or more machine learning prediction models, wherein the base option has a score above a threshold score, wherein the base option and the one or more matching base option candidates are ranked based on their corresponding scores;
utilizing the one or more machine learning prediction models selected based at least in part on the optimization goal to determine prediction values associated with alternative features for the base option, wherein the one or more machine learning prediction models were trained using training data to at least identify machine learning weight values associated with the alternative features for the one or more machine learning prediction models;
based on the prediction values, sorting at least a portion of the alternative features to generate an ordered list of at least the portion of the alternative features for the selected base option; and
providing the ordered list for use in manufacturing an alternative version of the selected base option with one or more of the alternative features in the ordered list.
2. The method of claim 1 , further comprising identifying one or more components of optimization goal, wherein the one or more components includes at least one of an optimization type and a target segment.
3. The method of claim 1 , wherein using the optimization goal to identify one or more matching base option candidates is based at least in part on past performance data associated with the one or more matching base option candidates.
4. The method of claim 1 , wherein using the optimization goal to identify one or more matching base option candidates is based at least in part on a variety metric of the one or more matching base option candidates.
5. The method of claim 1 , wherein the database of base option candidates includes a catalog of products and the selection of a selected base option is made by a user.
6. The method of claim 1 , wherein utilizing the one or more machine learning prediction models includes selecting training data based on the optimization goal.
7. The method of claim 1 , wherein sorting at least a portion of the alternative features includes selecting the one or more machine learning prediction models based on the optimization goal to predict a set of features including the at least a portion of the alternative features.
8. The method of claim 1 , wherein utilizing the one or more machine learning prediction models includes determining a combination of at least two features and identifying an associated machine learning weight value for the combination of the at least two features.
9. The method of claim 1 , wherein utilizing the one or more machine learning prediction models includes supervised learning of the training data.
10. The method of claim 1 , wherein utilizing the one or more machine learning prediction models includes determining a role of an alternative feature in a predicted performance of a base option.
11. The method of claim 1 , further comprising selecting the at least the portion of the alternative features based on at least one of natural language processing and computer vision, wherein the alternative features are filtered based on eligibility for the selected base option.
12. The method of claim 1 , further comprising:
receiving a selection of at least one of the alternative features in the ordered list;
identifying one or more example base options having the selected at least one of the alternative features; and
providing the one or more example base options.
13. The method of claim 1 , wherein the optimization goal includes predicted performance with respect to a segment.
14. The method of claim 1 , wherein an alternative feature is selected for inclusion in the ordered list of alternative features based at least in part on a sales metric of a set of features including the alternative feature.
15. The method of claim 1 , wherein an alternative feature is selected for inclusion in the ordered list of alternative features based at least in part on a rating metric of a set of features including the alternative feature.
16. The method of claim 1 , wherein an alternative feature is selected for inclusion in the ordered list of alternative features based at least in part on a variety metric of an inventory having a set of features including the alternative feature.
17. The method of claim 1 , further comprising automatically generating a design of a product, wherein the product includes the alternative version of the selected base option with one or more of the alternative features in the ordered list.
18. A system for optimizing computer machine learning, comprising:
a communications interface configured to:
receive an optimization goal; and
receive a selection of a base option among one or more matching base option candidates based in part on a ranking of the base option among the one or more matching base option candidates, wherein the base option is ranked based in part on a divergence between actual performance that includes measured sales data of the base option and performance that includes expected sales data of the base option predicted by one or more machine learning prediction models, wherein the base option has a score above a threshold score, wherein the base option and the one or more matching base option candidates are ranked based on their corresponding scores;
a processor configured to:
utilize the one or more machine learning prediction models selected based at least in part on the optimization goal to determine prediction values associated with alternative features for the selected base option, wherein the one or more machine learning prediction models were trained using training data to at least identify machine learning weight values associated with the alternative features for the one or more machine learning prediction models;
based on the prediction values, sort at least a portion of the alternative features to generate an ordered list of at least the portion of the alternative features for the selected base option; and
provide the ordered list for use in manufacturing an alternative version of the selected base option with one or more of the alternative features in the ordered list.
19. A computer program product for optimizing computer machine learning, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving an optimization goal;
using the optimization goal to search a database of base option candidates to identify one or more matching base option candidates that at least in part matches the optimization goal;
receiving a selection of a base option among the one or more matching base option candidates based in part on a ranking of the base option among the one or more matching base option candidates, wherein the base option is ranked based in part on a divergence between actual performance that includes measured sales data of the selected base option and performance that includes expected sales data of the base option predicted by one or more machine learning prediction models, wherein the base option has a score above a threshold score, wherein the base option and the one or more matching base option candidates are ranked based on their corresponding scores;
utilizing the one or more machine learning prediction models selected based at least in part on the optimization goal to determine prediction values associated with alternative features for the selected base option, wherein the one or more machine learning prediction models were trained using training data to at least identify machine learning weight values associated with the alternative features for the one or more machine learning prediction models;
based on the prediction values, sorting at least a portion of the alternative features to generate an ordered list of at least the portion of the alternative features for the selected base option; and
providing the ordered list for use in manufacturing an alternative version of the selected base option with one or more of the alternative features in the ordered list.