Improving Receipt Classification Through Text Processing

10sheet is a third party software company aimed at providing easy bookkeeping to client companies. One of the steps in bookkeeping is classifying receipts based on their content. Without relying on a human bookkeeper, 10sheet uses a classification algorithm to build an automatic classifier for this purpose. However, such a classifier needs to have a high performance to be trusted with real world tasks. In this project, an investigation will be conducted of various methods of preprocessing the input text used in building the classifier and the classification algorithms to identify solutions and enhancements that have the potential to boost the current performance of the automatic classifier for receipts. Then the chosen methods out of the proposed ones for will be prototyped and evaluated for inclusion in, and advancement of, the company’s system.

Faculty Supervisor:

Oliver Schulte

Student:

Partner:

10sheet Services Inc

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Simon Fraser University

Program: