Electronic document handling was first used in the automotive industry in the early 1970’s, the way of communicating electronic at the time was concerned with the communication way of EDI (Hsieh, 2004). In the beginning of 2000 a new way of communicating electronic documents was introduced with the emergence of VAN-operators (Hsieh, 2004). This technology of communicating electronic invoices has shown to be less complex for the businesses than the previous EDI connections. The VAN-operators enable companies regardless of size, ERP, also known as Enterprise Resource Planning, system, formats or transaction volume to send and receive electronic invoices. The subject of electronic invoice handling have become increasingly debated, mainly because of the legislations taking place all over Europe, and as well as the environmental impact by business transactions being sent by paper. The objective of this thesis is to examine the challenges, solutions and outcomes for companies switching to electronic invoice handling. The data collected for the thesis is divided into two parts. The first part consist of information retrieved by previous literature as well as internet sources. The second part concerns the case studies conducted for the thesis in respect to our research questions. For this reason Scandinavian companies have been interviewed, with different precondition as in size, industry, transaction volume and IT structure. The findings from the first and second part have been analyzed and conclusion have been made, we suggest using a VAN-operators, which have shown to be the most appropriate alternative for companies that are implementing electronic invoice handling. The result of this thesis can be used as a guideline for companies when considering a switch from manual to electronic invoice handling.

Companies often process invoices manually, therefore automation could reduce manual labor. The aim of this thesis is to evaluate which OCR-engine, Tesseract or OCRopus, performs best at interpreting invoices. This thesis also evaluates if it is possible to use machine learning to automatically process invoices based on previously stored data. By interpreting invoices with the OCR-engines, it results in the output text having few spelling errors. However, the invoice structure is lost, making it impossible to interpret the corresponding fields. If Naïve Bayes is chosen as the algorithm for machine learning, the prototype can correctly classify recurring invoice lines after a set of data has been processed. The conclusion is, neither of the two OCR-engines can interpret the invoices to plain text making it understandable. Machine learning with Naïve Bayes works on invoices if there is enough previously processed data. The findings in this thesis concludes that machine learning and OCR can be utilized to automatize manual labor. / Företag behandlar oftast fakturor manuellt och en automatisering skulle kunna minska fysiskt arbete. Målet med examensarbetet var att undersöka vilken av OCR-läsarna, Tesseract och OCRopus som fungerar bäst på att tolka en inskannad faktura. Även undersöka om det är möjligt med maskininlärning att automatiskt behandla fakturor utifrån tidigare sparad data. Genom att tolka text med hjälp av OCR-läsarna visade resultaten att den producerade texten blev språkligt korrekt, men att strukturen i fakturan inte behölls vilket gjorde det svårt att tolka vilka fält som hör ihop. Naïve Bayes valdes som algoritm till maskininlärningen och resultatet blev en prototyp som korrekt kunde klassificera återkommande fakturarader, efter att en mängd träningsdata var behandlad. Slutsatsen är att ingen av OCR-läsarna kunde tolka fakturor så att resultatet kunde användas vidare, och att maskininlärning med Naïve Bayes fungerar på fakturor om tillräckligt med tidigare behandlad data finns. Utfallet av examensarbetet är att maskininlärning och OCR kan användas för att automatisera fysiskt arbete.