Segmentation via principal component analysis for perceptron classification

Maneno, Khamis Mwero; Rimiru, Richard; Otieno, Calvins

doi:10.1145/3415088.3415128

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, while K-means clustering has been widely studied in retail customer segmentation, there is a limited body of literature specifically focusing on grocery stores in the Kenyan context. Given the unique cultural and economic factors influencing consumer behavior in Kenya, the application of customer segmentation techniques in this setting becomes of paramount importance.A notable study by Maneno et al [4] explored customer segmentation in the Kenyan retail sector using a different clustering algorithm. Their findings indicated significant variations in shopping preferences across different regions of Kenya, highlighting the need for tailored marketing strategies.…”

Section: Literature Reviewmentioning

confidence: 99%

Application Of K-Means Clustering For Customer Segmentation In Grocery Stores In Kenya

Omol,

Onyangor,

Mburu

et al. 2024

International Journal of Science, Technology & Management

View full text Add to dashboard Cite

The retail industry, particularly in the context of grocery stores, plays a vital role in meeting consumers' daily needs. To optimize marketing strategies and enhance customer satisfaction, understanding customer behavior and preferences is crucial. Customer segmentation, a powerful market research technique, enables businesses to group customers with shared characteristics into distinct segments, allowing targeted and personalized approaches. This article explores the application of the K-means clustering algorithm for customer segmentation in grocery stores within the unique context of Kenya. By leveraging transactional and demographic data from diverse grocery stores across Kenya, the study aims to identify homogeneous customer groups with similar purchasing behaviors and preferences. The data collection process involved obtaining consent from store owners and ensuring data privacy and security. Following data preprocessing, K-means clustering was applied, and various validation techniques were utilized to determine the optimal number of clusters. The results yielded valuable insights into customer segments, aiding the identification of key customer groups and their distinct preferences.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Application Of K-Means Clustering For Customer Segmentation In Grocery Stores In Kenya

Omol,

Onyangor,

Mburu

et al. 2024

International Journal of Science, Technology & Management

View full text Add to dashboard Cite

show abstract

“…Reference [12] proposes a method for segmenting medical images using principal component analysis (PCA). The method first uses PCA to reduce the dimensionality of the image data.…”

Section: Related Workmentioning

confidence: 99%

Comparison of Supervised Learning Algorithms on a 5G Dataset Reduced via Principal Component Analysis (PCA)

Gonzalez-Franco,

Preciado-Velasco,

Lozano-Rizk

et al. 2023

Future Internet

View full text Add to dashboard Cite

Improving the quality of service (QoS) and meeting service level agreements (SLAs) are critical objectives in next-generation networks. This article presents a study on applying supervised learning (SL) algorithms in a 5G/B5G service dataset after being subjected to a principal component analysis (PCA). The study objective is to evaluate if the reduction of the dimensionality of the dataset via PCA affects the predictive capacity of the SL algorithms. A machine learning (ML) scheme proposed in a previous article used the same algorithms and parameters, which allows for a fair comparison with the results obtained in this work. We searched the best hyperparameters for each SL algorithm, and the simulation results indicate that the support vector machine (SVM) algorithm obtained a precision of 98% and a F1 score of 98.1%. We concluded that the findings of this study hold significance for research in the field of next-generation networks, which involve a wide range of input parameters and can benefit from the application of principal component analysis (PCA) on the performance of QoS and maintaining the SLA.

show abstract