Financial statements fraud detection from unstructured data using deep learning

  • This research paper explores the application of the Universal Language Model Fine-tuning (ULMFiT) technique, a novel deep transfer learning approach in the Natural Language Processing (NLP) field, to the financial statements fraud detection task. Additionally, the artifact investigated a simpler model, represented by a one-dimensional Convolutional Neural Network (CNN). Both methods have been assessed with respect to the training time and predefined evaluation metrics. Overall, ULMFiT turned out to be considerably more computationally expensive to train and achieved an accuracy of 77% with F-measure of 13%, if used with a decision boundary of 0.5, and accuracy of 59% with F-measure of 42%, if calculated with a threshold of 0.2. In contrast, CNN model trained significantly faster and obtained the following metrics: accuracy of 82% with F-measure of 42% for threshold 0.5, and accuracy of 83% with F-measure of 58% for threshold 0.2. As a result, ULMFiT has been outperformed by one-dimensional CNN on all examined metrics. The results are reported by using two different values for decision boundary due to the precision-recall trade-off, depending on the use case. In addition, this thesis investigated the impact of data preprocessing. The findings have shown that removing all numbers and special symbols with supplementary text truncation, limiting the sequence length, had a positive effect on both models, mentioned above.

Download full text files

  • Korchagina,Irina_MA_2019.pdf
    eng

    verfügbar innerhalb des Netzes der HWR Berlin

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Irina Korchagina
URN:urn:nbn:de:kobv:b721-opus4-17371
Referee:Roland Müller
Advisor:Markus Löcher
Document Type:Master's Thesis
Language:English
Date of first Publication:2019/08/13
Publishing Institution:Hochschulbibliothek HWR Berlin
Granting Institution:Hochschule für Wirtschaft und Recht Berlin
Date of final exam:2019/01/23
Release Date:2019/08/13
Tag:Annual Reports; Deep Learning; Financial Statements; Fraud Detection; LSTM; Transfer Learning; ULMFiT
Page Number:97
Institutes:FB I - Wirtschaftswissenschaften / Business Intelligence and Process Management M.Sc.
Licence (German):License LogoUrheberrechtsschutz