Miniatura

Fitxers

tfm_oshea_jd.pdf (1.6 MB)
fuxi-main.zip (9.74 MB)

Tipus de document

Treball de fi de màster

Data de publicació

2023-06-30

Llicència de publicació

cc-by-nc-nd (c) JD O'Shea, 2023
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/214380

Using deep learning techniques in click-through rate prediction focusing on a DeepFM model and a comparative analysis of the volatility of prediction vectors of different models

Títol de la revista

Autors

Director/Tutor

ISSN de la revista

Títol del volum

Recurs relacionat

Resum

Using deep learning in prediction of click-through rate (CTR) is becoming main stream for advertisers engaging in real time bidding (RTB). However, there are implications for adopting a deep learning algorithm to predict CTR and to evaluate a user impression while engaging in real time bidding. In this paper, we explore two state of the art deep learning methods, DeepFM and DCN, using Logistic Regression and Factorization Machine models as a benchmark. We explore their predictive power and the trade off of each model time with respect to training times, inference times, effects of dimension of input data when using hashing buckets, and volatility of prediction of models from training to training. We experiment comprehensively throughout our research with the goal of striking a balance between discovering the best predictor of CTR to enhance a company’s RTB strategy whilst understanding the cost of chasing a (usually) more complex implementation in order to obtain an increase in predictive power. The deep learning models outperform Logistic Regression in RIG, with the DeepFM model achieving the best RIG however the opposite is true for model complexity, training, and inference times. Increasing the hashing bucket size leads to better performances across Logistic Regression. Finally, we look at the volatility of a models prediction vector under retraining with different training data conditions while keeping in mind the goal of developing a real bidding algorithm that takes as input the output of our CTR prediction model.

Descripció

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2022-2023. Tutor: Jordi Vitrià i Marca

Matèries

Aprenentatge automàtic, Anàlisi de regressió, Algorismes computacionals, Treballs de fi de màster

Matèries (anglès)

Machine learning, Regression analysis, Computer algorithms, Master's thesis

Citació

Col·leccions

Màster Oficial - Fonaments de la Ciència de Dades
Programari - Treballs de l'alumnat

Citació

O'HEA, Jd. Using deep learning techniques in click-through rate prediction focusing on a DeepFM model and a comparative analysis of the volatility of prediction vectors of different models. [consulta: 25 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/214380]

Exportar metadades

JSON - METS

Compartir registre