Abstract
This disclosure describes techniques to automatically generate stories for users based on their spending histories. The stories can be formed by aggregating or clustering transactions around common themes or attributes using templatized search. Templatized searches are filled on the fly, and with user permission, are executed over the user’s transaction history to obtain matching results. The search results are used to form a story that can be displayed to the user in engaging and insightful ways, e.g., spending locations highlighted on maps; spending histograms; spending versus time; summary statistics (sum, average, max/min); etc.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Kota, Nithya; Dewan, Maneesh; Mallya, Ganesh; and Chhugani, Jatin, "Templatized, Attribute-driven Search to Generate Stories", Technical Disclosure Commons, (August 11, 2022)
https://www.tdcommons.org/dpubs_series/5308