Browsing by Author "Dag,T."

Now showing 1 - 2 of 2

Customer Purchase Intent Prediction Using Feature Aggregation on E-Commerce Clickstream Data
(Institute of Electrical and Electronics Engineers Inc., 2024) Tokuc,A.A.; Dag,T.
This paper presents a machine learning model for predicting customer purchase intent using e-commerce clickstream data. The model is built using the LightGBM framework, chosen for its efficiency in handling large-scale datasets and complex feature interactions. Key challenges addressed include the high dimensionality of clickstream data, the inherent class imbalance between purchase and non-purchase sessions, and the temporal variability of user behavior. The feature engineering process involved creating and selecting features that capture relevant user behaviors, such as session duration, event counts, and interaction diversity. The model was evaluated using ROC-AUC, F1-score, precision, and recall metrics, demonstrating strong performance in identifying sessions likely to result in a purchase. This study contributes to the field of e-commerce analytics by providing a robust framework for conversion prediction, enabling more effective customer engagement strategies. Our findings underscore the potential of machine learning to enhance e-commerce conversion rates, thereby optimizing customer engagement. © 2024 IEEE.
Citation Count: 11
A novel image steganography technique based on similarity of bits pairs
(Institute of Electrical and Electronics Engineers Inc., 2017) Shehzad,D.; Dag,T.
Steganography is one of the most important information hiding mechanism, which can be used along with cryptography for providing adequate data security. The common Steganographic mediums used are text, image, audio and video for hiding secret information. In the case of image medium, mostly least significant bits of pixels of a cover image are used for hiding secret information. In this paper, a new technique based on pairs matching is proposed, data bits of the message to be secured are arranged in pairs and image pixel bits are also arranged pairwise. The pixel bits are represented in forms of pairs as, 7th and 6th bits makes 3rd pair, 6th and 5th bits are named as 2nd pair, while 5th and 4th bits are denoted with 1st pair and the last one 4th and 3rd pair represented as the 0th pair. The secret message bits are compared with all pairs and replace the least two significant bits with respective matched pair number. If no pair is matched, then replace the 0th pair with message bits, and replace two LSB with pair no 0. The proposed technique shows good quality of stego image, along with acceptable PSNR and also carries the high capacity of secret message. By comparing the results with existing techniques, the proposed technique shows good results. © 2017 IEEE.