This thesis explores if classification of financial documents is possible through machine learning with implementations of Naïve Bayes and a rule-based method. It further explores the differences between these approaches, including a version of Naïve Bayes that includes a decision threshold. Incentives behind a non-human classifier are evaluated from an organizational perspecitive. The machine learning implementation was trained on historical data supplied by the client, and the rules for the second method were established by conducting an interview with one of the employees who previously has worked with classification. The results show that all three implementations are sufficient viewing the accuracy, precision and execution time. The ti...
Att manuellt hantera och klassificera stora mängder textdokument tar mycket tid och kräver mycket pe...
Several studies have been conducted within machine learning, and various variations have been applie...
The field of bankruptcy prediction has experienced a notable increase of interest in recent years. M...
This thesis explores if classification of financial documents is possible through machine learning w...
Automatiserad dokumentklassificering är en process eller metod som syftar till att bearbeta ochhante...
Document classification is a growing interest in the research of text mining. Correctly identifying ...
Document classification is a growing interest in the research of text mining. Correctly identifying ...
Balcão 2020 is a fund-granting platform currently enduring issues related to ensuring that the docu...
This thesis investigates imbalanced Swedish text financial datasets, specifically receipt classifica...
The fields of artificial intelligence and machine learning are rapidly transforming the global techn...
The number of documents in the form of books, scientific articles, reports etc. is always increasing...
Companies with more than 3 million SEK in revenue per year are by law in Sweden required to bookkeep...
The aim of this study is to evaluate feasibility of using Bayes classifiers for predicting corporate...
Abstract:- Supervised learning plays a significant role in predicting the behavior of new data, base...
Att identifiera finansiella svårigheter vid bedömning av ett företags ekonomiska situation är väsent...
Att manuellt hantera och klassificera stora mängder textdokument tar mycket tid och kräver mycket pe...
Several studies have been conducted within machine learning, and various variations have been applie...
The field of bankruptcy prediction has experienced a notable increase of interest in recent years. M...
This thesis explores if classification of financial documents is possible through machine learning w...
Automatiserad dokumentklassificering är en process eller metod som syftar till att bearbeta ochhante...
Document classification is a growing interest in the research of text mining. Correctly identifying ...
Document classification is a growing interest in the research of text mining. Correctly identifying ...
Balcão 2020 is a fund-granting platform currently enduring issues related to ensuring that the docu...
This thesis investigates imbalanced Swedish text financial datasets, specifically receipt classifica...
The fields of artificial intelligence and machine learning are rapidly transforming the global techn...
The number of documents in the form of books, scientific articles, reports etc. is always increasing...
Companies with more than 3 million SEK in revenue per year are by law in Sweden required to bookkeep...
The aim of this study is to evaluate feasibility of using Bayes classifiers for predicting corporate...
Abstract:- Supervised learning plays a significant role in predicting the behavior of new data, base...
Att identifiera finansiella svårigheter vid bedömning av ett företags ekonomiska situation är väsent...
Att manuellt hantera och klassificera stora mängder textdokument tar mycket tid och kräver mycket pe...
Several studies have been conducted within machine learning, and various variations have been applie...
The field of bankruptcy prediction has experienced a notable increase of interest in recent years. M...