Measuring relevance of datasets to a data science model

A computer program product for measuring relevance of datasets to data science models, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors, the program instructions executable to:

• from each of data science models, extract keywords, wherein the data science models include artificial intelligence models, machine learning models, and optimization models;
• determine first relative frequencies of respective ones of the keywords in each of the data science models, for each of sources in the data science models, wherein the sources in the data science models include tags of the data science models, free form natural language text, and identifiers in source code of the data science models;
• extract keywords in each of datasets to be used by the data science models;
• determine second relative frequencies of respective ones of the keywords in each of the datasets, for each of sources in the datasets, wherein the sources in the dataset include column names, dataset names, tags or other supplemental data associated with datasets, and string values from data rows;
• determine weights of the keywords, based on source categories of the keywords;
• calculate first aggregated relevant scores of respective ones of the keywords in each of the data science models, based on the first relative frequencies and the weights;
• calculate second aggregated relevant scores of respective ones of the keywords in each of the datasets, based on the second relative frequencies and the weights;
• provide a user with an order of relevance of the datasets to the data science models, based on the first aggregated relevant scores and the second aggregated relevant scores;
• and
• wherein a dataset is selected for a given data science model, based the order of the relevance.

A computer system for measuring relevance of datasets to data science models, the computer system comprising:

• one or more processors, one or more computer readable tangible storage devices, and program instructions stored on at least one of the one or more computer readable tangible storage devices for execution by at least one of the one or more processors, the program instructions executable to:
• from each of data science models, extract keywords, wherein the data science models include artificial intelligence models, machine learning models, and optimization models;
• determine first relative frequencies of respective ones of the keywords in each of the data science models, for each of sources in the data science models, wherein the sources in the data science models include tags of the data science models, free form natural language text, and identifiers in source code of the data science models;
• extract keywords in each of datasets to be used by the data science models;
• determine second relative frequencies of respective ones of the keywords in each of the datasets, for each of sources in the datasets, wherein the sources in the dataset include column names, dataset names, tags or other supplemental data associated with datasets, and string values from data rows;
• determine weights of the keywords, based on source categories of the keywords;
• calculate first aggregated relevant scores of respective ones of the keywords in each of the data science models, based on the first relative frequencies and the weights;
• calculate second aggregated relevant scores of respective ones of the keywords in each of the datasets, based on the second relative frequencies and the weights;
• provide a user with an order of relevance of the datasets to the data science models, based on the first aggregated relevant scores and the second aggregated relevant scores;
• and
• wherein a dataset is selected for a given data science model, based the order of the relevance.