An article of manufacture comprising a non-transitory computer accessible storage medium having stored thereupon a sequence of instructions which, when executed by at least one processor or at least one processor core executing one or more threads, causes the at least one processor or the at least one processor core to perform a set of acts for providing tax return information for an electronic tax return preparation and filing software application delivery model, the set of acts comprising:
- identifying, by at least one micro-processor of a computing system, a plurality of business clusters and a plurality of expense categories for the plurality of business clusters;
- extracting, by the at least one micro-processor of a computing system, description about a first characteristic of a specific user from an electronic tax return in an electronic tax return preparation and filing software application delivery model, the description expressed in natural language;
- generating, by the at least one micro-processor, a user description vector of at least a part of the description, the user description vector expressing the at least part of the description in a normalized form within a vector space;
- determining, by the at least one micro-processor, one or more business clusters from a plurality of business clusters within the vector space for the specific user by matching the user description vector with the one or more business clusters within the vector space;
- and
- selecting, by the at least one micro-processor, one or more expense categories for the electronic tax return of the specific user based in part or in whole upon at least one association between the selected one or more expense categories and the matched one or more business clusters.