AI-Driven Personal Finance Assistant with Voice, OCR, and Chatbot
Fuente:
Zenodo
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Recurso digital |
| Veröffentlicht: |
Zenodo
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866901840999743488 |
|---|---|
| author | Praveen C Mukeesh R Mohamed Inzamam S Divya S |
| author_facet | Praveen C Mukeesh R Mohamed Inzamam S Divya S |
| contents | This project is concerned with the creation of a personal finance management web application. The principal idea is to assist users to monitor their expenses, investments, and bills easily. It is hard to keep track of finances on a regular basis for many users and this system aims at making this process less demanding. The software is developed on the Django framework, which is applied to address user log-in, data storage, and safe storage and processing of financial records. The system has a chatbot to ensure that communication is easy among the users. The chatbot uses a fine-tuned DistilBERT model with natural language processing in order to provide users with an opportunity to enter queries in ordinary language. It can perform functions like the addition of costs and verification of financial records. An OCR module is also included to prevent manual typing of receipt data. In this module, EasyOCR is used along with a fine-tuned LayoutLM model trained on the SROIE dataset to extract item information and sums of money from receipt images. The extracted information is saved and utilized in tracking expenses, helping users save time when using the system daily. Collected data is analyzed by several machine learning methods. XGBoost is used to estimate return on investment, an Autoencoder is used for unusual spending behaviour detection, and Prophet is employed to investigate spending patterns. Results are presented in simple graphs and charts to enable users to comprehend their financial trends. The application is modularly structured so features can be updated in the future. Overall, the system aims for automation and simplicity: speech-based input, receipt scanners, and chatbot interactions minimize user effort and provide a convenient, easy-to-use personal finance management solution. |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19534317 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | AI-Driven Personal Finance Assistant with Voice, OCR, and Chatbot Praveen C Mukeesh R Mohamed Inzamam S Divya S Personal Finance NLP OCR Speech Recognition Machine Learning Chatbot This project is concerned with the creation of a personal finance management web application. The principal idea is to assist users to monitor their expenses, investments, and bills easily. It is hard to keep track of finances on a regular basis for many users and this system aims at making this process less demanding. The software is developed on the Django framework, which is applied to address user log-in, data storage, and safe storage and processing of financial records. The system has a chatbot to ensure that communication is easy among the users. The chatbot uses a fine-tuned DistilBERT model with natural language processing in order to provide users with an opportunity to enter queries in ordinary language. It can perform functions like the addition of costs and verification of financial records. An OCR module is also included to prevent manual typing of receipt data. In this module, EasyOCR is used along with a fine-tuned LayoutLM model trained on the SROIE dataset to extract item information and sums of money from receipt images. The extracted information is saved and utilized in tracking expenses, helping users save time when using the system daily. Collected data is analyzed by several machine learning methods. XGBoost is used to estimate return on investment, an Autoencoder is used for unusual spending behaviour detection, and Prophet is employed to investigate spending patterns. Results are presented in simple graphs and charts to enable users to comprehend their financial trends. The application is modularly structured so features can be updated in the future. Overall, the system aims for automation and simplicity: speech-based input, receipt scanners, and chatbot interactions minimize user effort and provide a convenient, easy-to-use personal finance management solution. |
| title | AI-Driven Personal Finance Assistant with Voice, OCR, and Chatbot |
| topic | Personal Finance NLP OCR Speech Recognition Machine Learning Chatbot |
| url | https://doi.org/10.5281/zenodo.19534317 |