Corpus ID: 6803737

A Logistic Regression Approach to Ad Click Prediction

  title={A Logistic Regression Approach to Ad Click Prediction},
  author={Gouthami Kondakindi},
This paper presents an empirical study of using different machine learning techniques to predict whether an ad will be clicked or not. We perform click prediction on a binary scale 1 for click and 0 for no click. We use clicks data from Avazu provided as a part of Kaggle competition as our data set. We perform feature selection to remove features that do not help improve classifier accuracy. We inspect data manually and also use feature selection capability of Vowpal Wabbit for this purpose. We… Expand

Figures and Tables from this paper

Progress Report : Predicting Which Recommended Content Users Click
Machine learning models can be used to predict which recommended content users will click on a given website. The given dataset contains millions of samples that map some feature about an ad or webExpand
Click Through Rate Prediction for Contextual Advertisment Using Linear Regression
A new technique is proposed in this paper to predict the CTR which will increase the overall revenue of the system by serving the advertisements more suitable to the viewers with the help of feature extraction and displaying the advertisements based on context of the publishers. Expand
CTR Prediction with User Behavior: An Augmented Method of Deep Factorization Machines
The experimental results on TikTok dataset demonstrate that the proposed behavior-empahsized algorithms achieve superior performance with less time consumption on this Click-Through-Rate prediction problems. Expand
Data Driven Resource Allocation for Distributed Machine Learning
In distributed machine learning, data is dispatched to multiple machines for processing. Traditional distributed Machine Learning systems dealing with high volume of data randomly distribute the dataExpand


Ad click prediction: a view from the trenches
The goal of this paper is to highlight the close relationship between theoretical advances and practical engineering in this industrial setting, and to show the depth of challenges that appear when applying traditional machine learning methods in a complex dynamic system. Expand
Predicting Click-Through Rates of New Advertisements Based on the Bayesian Network
This paper built a Bayesian network of the keywords that are used to describe the ads in a certain domain, called keyword BN and abbreviated as KBN and proposed an algorithm for approximate inferences of the KBN to find similar keywords with those that describe the new ads. Expand
Scaling Factorization Machines to Relational Data
This work solves the issue of standard learning algorithms based on the design matrix representation cannot scale to relational predictor variables by making use of repeating patterns in the design Matrix which stem from the underlying relational structure of the data. Expand
Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval
The naive Bayes classifier, currently experiencing a renaissance in machine learning, has long been a core technique in information retrieval, and some of the variations used for text retrieval and classification are reviewed. Expand
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
This work describes and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal functions that can be chosen in hindsight. Expand
Principal Component Analysis on Human Development Indicators of China
In this study, we used the weightedprincipal component analysis to measure and analyzethe progress of human development inChinese provinces since 1990. The trends of thehuman development in theExpand
Vowpal Wabbit open tool
    Vowpal Wabbit open tool. ˜ vw
    • Vowpal Wabbit open tool. ˜ vw