Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The profession of chartered accountant has evolved rapidly in recent years, thanks to the advent of digital solutions. The role of the accountant is becoming that of an advisor. The accounting firm Comptarama has understood this and has bet on an innovative business model. They are determined to offer their clients, mainly very small businesses, quality advice at a fair price. In order to do so, they have opted for the use of new technologies, such as the digitalisation of the clients’ documents and the use of artificial intelligence for encoding.
With this innovative approach, the company wishes to provide its accountants with high-performance tax estimation tools. At present, they do not have any. The purpose of this dissertation is to develop a single solution for simulating the remuneration of company directors and the advance tax payments of self-employed persons. Emphasis will be placed, on the one hand, on the estimation of social security contributions and, on the other hand, on the determination of taxes. The aim of the tool is to unify working methods, improve the accuracy of estimates and increase customer satisfaction. 
To achieve these objectives, the reflection will be based on an in-depth analysis of current estimation methods and a theoretical approach. Then, processes will be mapped to define the characteristics of the future tool. Finally, they will be transcribed into a functional calculator. 
This future tool, which will be available to employees, will then have to be made available to customers. A mobile application will connect the accountant to his client, like banking applications. The aim is for clients to be able to make estimates themselves in a simplified manner. They will be able to have their entire accounting situation at their fingertips.

digitalisation, small businesses, tax estimation tools, social security contributions, advance tax payments, calculator --- Sciences économiques & de gestion > Comptabilité & audit

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Today, for Billy and many accounting fiduciaries, invoice information is usually encoded manually by the accountant or by a low-performance software, so a lot of time is wasted on encoding and not on advice. Indeed, During the year 2021, Billy's accountants spent 37% of their time on encoding. Consequently, the recognition of fields in a semi-structured document of variable layout (i.e. invoice) is a growing need for accountants, and especially for Billy, in which the number of new customers increasing every month. Nonetheless, the text and image pre-training strategies of the Transformer architecture model have proven to be efficient in the field of document understanding. Thus, several OCR tools were tested, and the Azure OCR tool, which gave the higher performances, was selected to extract text from image invoice of Billy's customers in order to create datasets. Indeed, this allows the elaboration of four datasets partially annotated, named BTT, BTT Star, BTT QV, and BTT QV Date, which were created from scanned purchase, sales documents, and their accounting encoding in the accounting Horus software. Then, the fine-tuning of the pre-trained multi-modal models LayoutLMv2_BASE, LayoutLMv2_LARGE, and LayoutXLM_BASE has been done. In contrast to the previous architectural models of the LayoutLM family, these models include, in addition to the text and layout information, information that can be provided by the document image. Thanks to spatial-aware self-attention mechanisms integrated in the Transformer architecture model, it is able to interpret relations through different bounding boxes.&#13;According to Billy's accountants, invoice information is recognized by Horus in 70\% of the cases. During the experiments conducted in this Master thesis, it was shown that on token classification tasks, higher results were obtained for the the different datasets in terms of F1-score: BTT (0.9420), BTT Star (0.9553), BTT QV ( 0.9413) and BTT QV Date (0.9472). In addition, similar state-of-the-art results were obtained using the open source CORD dataset which gives an F1-score of 0.9354. Moreover, the impact of a pre-trained model on a dataset composed only of English documents LayoutXLM_BASE) was studied in comparison with a pre-trained model on a multi-lingual dataset (LayoutLMv2_BASE) to classify tokens on documents mostly in French. The results show that the pre-trained model does not have a great impact on the final result for this type of task: (BTT (0.9323 -> 0.9338), BTT Star (0.9354 -> 0.9468), BTT QV (0.9229 <- 0.8955), and BTT QV Date (0.9411 <- 0.9328). To conclude, since the results of the four datasets were close to each other, the dataset BTT Star produced the best results. This dataset has the largest number of labels and is the most widely distributed over the documents, leading to the hypothesis that a more widely distributed set of labels provides better results.&#13;Finally, to concretize this work, a web application was developed in parallel in order to use this tool in everyday life for both the accountants and the customers.

Machine learning, Deep learning --- Ingénierie, informatique & technologie > Sciences informatiques