Online mail classifier using Deep Learning
This thesis has been developed at NTTData for an external client. The client requires an autonomous mail classifier since they currently classify mails manually. The thesis consists in the development of a Deep Learning model for the classification of emails in categories, according to its typology,...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Fecha de publicación: | 2022 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/365800 |
| Acceso en línea: | https://hdl.handle.net/2117/365800 |
| Access Level: | acceso embargado |
| Palabra clave: | Deep learning Natural language processing (Computer science) Deep Learning Scorer Online NLP autonomous AutoML Aprenentatge profund Tractament del llenguatge natural (Informàtica) Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
| Sumario: | This thesis has been developed at NTTData for an external client. The client requires an autonomous mail classifier since they currently classify mails manually. The thesis consists in the development of a Deep Learning model for the classification of emails in categories, according to its typology, using a scorer Online. The classification is done in real time. The model created is fully autonomous; the new mails are ingested daily, the model is trained monthly and the scorer is updated with the new model. This model has been productized on the client?s platform Another innovative aspect is the use of an AutoML tool to perform the data exploration and the viability study of the project, optimizing the time dedicated to these phases. |
|---|