Representation of Click-Stream DataSequences for Learning User Navigational Behavior by Using Embeddings

Olmezogullari, Erdi; Aktaş, Mehmet S.

doi:10.1109/bigdata50022.2020.9378437

Cited by 33 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exist studies that focus on analyzing the quality of the software [45,46]. However, in this study, we leave out the software quality analysis for future work.There are studies that focus on understanding users' actions by analyzing the user-system interaction data [47][48][49]. This study analyzes the users' behaviors based on their psychometric test data.…”

Section: Literature Reviewmentioning

confidence: 99%

Credit Risk Prediction Based on Psychometric Data

Duman,

Aktas,

Yahsi

2023

Computers

Self Cite

View full text Add to dashboard Cite

In today’s financial landscape, traditional banking institutions rely extensively on customers’ historical financial data to evaluate their eligibility for loan approvals. While these decision support systems offer predictive accuracy for established customers, they overlook a crucial demographic: individuals without a financial history. To address this gap, our study presents a methodology for a decision support system that is intended to assist in determining credit risk. Rather than solely focusing on past financial records, our methodology assesses customer credibility by generating credit risk scores derived from psychometric test results. Utilizing machine learning algorithms, we model customer credibility through multidimensional metrics such as character traits and attitudes toward money management. Preliminary results from our prototype testing indicate that this innovative approach holds promise for accurate risk assessment.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Credit Risk Prediction Based on Psychometric Data

Duman,

Aktas,

Yahsi

2023

Computers

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are studies that focus on understanding the user behaviors by analyzing user actions in different domains [28,31,34,35,38]. Also, some studies investigate the software quality [32,33].…”

Section: Literature Surveymentioning

confidence: 99%

A Framework for In-Car Loading Optimization Problem

Avcı,

Özbey,

Özen

et al. 2023

OPRD

View full text Add to dashboard Cite

Speed is a crucial evaluation criterion in the cargo transportation industry. The processes carried out during transfers before cargo reaches the destination unit are vital for timely delivery. Time spent at cargo distribution centers should be minimized, the maximum number of packages should be transported in a single action between transfers, and cargo vehicles should be used as accurately and efficiently as possible. Minimizing unused space inside the vehicles and ensuring that vehicles at cargo transfer centers are arranged correctly and efficiently for faster departures and increased cargo capacity are of great importance. In pursuit of this goal, the present research concentrates on optimizing the loading of vehicle interiors. This investigation proposes a method that determines the optimal dimensions of packages to be loaded within the vehicle, with the intention of maximizing the number of cargo packages while minimizing the interior volume used. A preliminary implementation of the suggested approach has been created. This developed prototype application can assist cargo transportation companies in planning their cargo loading and optimizing the utilization of vehicle interiors. The efficacy of the prototype application was evaluated using a representative vehicle loading dataset, and the results demonstrate its success.

show abstract

“…Different from these studies, we mainly focus on time series prediction data analysis process and leave out the distributed computing aspects of it as out of scope. There are data encoding methods used to understand users' actions to model the data in different domains [17][18][19][20][21]. In this study, we investigate the effects of stacked autoencoder and wavelet transformation data preprocessing techniques on time series prediction.…”

Section: Literature Reviewmentioning

confidence: 99%

An Experimental Study Investigating The Effects of Data Pre-processing Methods on Deep Learning Based Time Series Data Prediction

Aktas,

Yilmaz,

Karabacak

2023

Preprint

View full text Add to dashboard Cite

Time-series analysis is a widely used technique across various fields and industries, as it helps in understanding, predicting, and forecasting the behavior of data points over time. These fields include but are not limited to finance, economics, healthcare, transportation, etc. In the case of this paper, we have focused on finance. Predicting future values of financial time series offers several benefits. Accurate forecasts can help investors make better decisions about their investments. To predict future values, deep learning algorithms are commonly used since it is an effective method with complex data. In this study, we conduct a study that investigates the use of different data pre-processing techniques on deep learning algorithms in predicting the time series values. To conduct this experimental study, we utilize an open source software, which using long short-term memory technique as the representative deep learning technique, published in github software code repository platform. With this study, we investigate the effects of autoencoder and discrete wavelet transform data pre-processing techniques in time-series prediction. We discuss the details of the experimental study and report our results. The results show that time series prediction (using backtesting methodology) without any data pre-processing leads to 12.6% for mean absolute percentage error. The results also show that, time series prediction with the data preprocessing techniques (Wavelet Transform and Stacked Autoencoder) lead to 3.4%

show abstract

Representation of Click-Stream DataSequences for Learning User Navigational Behavior by Using Embeddings

Cited by 33 publications

References 12 publications

Credit Risk Prediction Based on Psychometric Data

Credit Risk Prediction Based on Psychometric Data

A Framework for In-Car Loading Optimization Problem

An Experimental Study Investigating The Effects of Data Pre-processing Methods on Deep Learning Based Time Series Data Prediction

Contact Info

Product

Resources

About