arXiv subjects

Ismail Hakki Toroslu

Publications and source records attributed to Ismail Hakki Toroslu.

6 recordsLinked to original sources

arXiv2025

Fair for a few: Improving Fairness in Doubly Imbalanced Datasets

Fairness has been identified as an important aspect of Machine Learning and Artificial Intelligence solutions for decision making. Recent literature offers a variety of approaches for debiasing, however many of them fall short when the data collection is imbalanced. In this paper, we focus on a particular case, fairness in doubly imbalanced datasets, such that the data collection is imbalanced both for the label and the groups in the sensitive attribute. Firstly, we present an exploratory analysis to illustrate limitations in debiasing on a doubly imbalanced dataset. Then, a multi-criteria based solution is proposed for finding the most suitable sampling and distribution for label and sensitive attribute, in terms of fairness and classification accuracy

cs.LG↗

arXiv2024

NeSHFS: Neighborhood Search with Heuristic-based Feature Selection for Click-Through Rate Prediction

Click-through-rate (CTR) prediction plays an important role in online advertising and ad recommender systems. In the past decade, maximizing CTR has been the main focus of model development and solution creation. Therefore, researchers and practitioners have proposed various models and solutions to enhance the effectiveness of CTR prediction. Most of the existing literature focuses on capturing either implicit or explicit feature interactions. Although implicit interactions are successfully captured in some studies, explicit interactions present a challenge for achieving high CTR by extracting both low-order and high-order feature interactions. Unnecessary and irrelevant features may cause high computational time and low prediction performance. Furthermore, certain features may perform well with specific predictive models while underperforming with others. Also, feature distribution may fluctuate due to traffic variations. Most importantly, in live production environments, resources are limited, and the time for inference is just as crucial as training time. Because of all these reasons, feature selection is one of the most important factors in enhancing CTR prediction model performance. Simple filter-based feature selection algorithms do not perform well and they are not sufficient. An effective and efficient feature selection algorithm is needed to consistently filter the most useful features during live CTR prediction process. In this paper, we propose a heuristic algorithm named Neighborhood Search with Heuristic-based Feature Selection (NeSHFS) to enhance CTR prediction performance while reducing dimensionality and training time costs. We conduct comprehensive experiments on three public datasets to validate the efficiency and effectiveness of our proposed solution.

cs.IR↗

arXiv2014

Secure Logical Schema and Decomposition Algorithm for Proactive Context Dependent Attribute Based Access Control

Traditional database access control mechanisms use role based methods, with generally row based and attribute based constraints for granularity, and privacy is achieved mainly by using views. However if only a set of views according to policy are made accessible to users, then this set should be checked against the policy for the whole probable query history. The aim of this work is to define a proactive decomposition algorithm according to the attribute based policy rules and build a secure logical schema in which relations are decomposed into several ones in order to inhibit joins or inferences that may violate predefined privacy constraints. The attributes whose association should not be inferred, are defined as having security dependency among them and they form a new kind of context dependent attribute based policy rule named as security dependent set. The decomposition algorithm works on a logical schema with given security dependent sets and aims to prohibit the inference of the association among the elements of these sets. It is also proven that the decomposition technique generates a secure logical schema that is in compliance with the given security dependent set constraints.

cs.DB↗

arXiv2014

Task Assignment in Tree-Like Hierarchical Structures

Most large organizations, such as corporations, are hierarchical organizations. In hierarchical organizations each entity in the organization, except the root entity, is a sub-part of another entity. In this paper we study the task assignment problem to the entities of tree-like hierarchical organizations. The inherent tree structure introduces an interesting and challenging constraint to the standard assignment problem. When a task is assigned to an entity in a hierarchical organization, the whole entity, including its sub-entities, is responsible from the execution of that particular task. In other words, if an entity has been assigned to a task, neither its descendants nor its ancestors can be assigned to a task. Sub-entities cannot be assigned as they have an ancestor already occupied. Ancestor entities cannot be assigned since one of their sub-entities has already been employed in an assignment. In the paper, we formally introduce this new version of the assignment problem called Maximum Weight Tree Matching ($MWTM$), and show its NP-hardness. We also propose an effective heuristic solution based on an iterative LP-relaxation to it.

cs.DS↗

arXiv2013

Link Based Session Reconstruction: Finding All Maximal Paths

This paper introduces a new method for the session construction problem, which is the first main step of the web usage mining process. Through experiments, it is shown that when our new technique is used, it outperforms previous approaches in web usage mining applications such as next-page prediction.

cs.DB↗

arXiv2008

Discovering More Accurate Frequent Web Usage Patterns

Web usage mining is a type of web mining, which exploits data mining techniques to discover valuable information from navigation behavior of World Wide Web users. As in classical data mining, data preparation and pattern discovery are the main issues in web usage mining. The first phase of web usage mining is the data processing phase, which includes the session reconstruction operation from server logs. Session reconstruction success directly affects the quality of the frequent patterns discovered in the next phase. In reactive web usage mining techniques, the source data is web server logs and the topology of the web pages served by the web server domain. Other kinds of information collected during the interactive browsing of web site by user, such as cookies or web logs containing similar information, are not used. The next phase of web usage mining is discovering frequent user navigation patterns. In this phase, pattern discovery methods are applied on the reconstructed sessions obtained in the first phase in order to discover frequent user patterns. In this paper, we propose a frequent web usage pattern discovery method that can be applied after session reconstruction phase. In order to compare accuracy performance of session reconstruction phase and pattern discovery phase, we have used an agent simulator, which models behavior of web users and generates web user navigation as well as the log data kept by the web server.

cs.DB↗