RFM Based Market Segmentation Approach Using Advanced K-means and Agglomerative Clustering: A Comparative Study

Shihab, Sabbir Hossain; Afroge, Shyla; Mishu, Sadia Zaman

doi:10.1109/ecace.2019.8679376

Cited by 22 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, Ghosal et al (2020), in their review, present K-Means and hierarchical algorithms as the most common methods for a market analysis. Exemplary studies using clustering algorithms such as K-Means, Ward, agglomerative clustering, or modified K-Means models and as selected features recency, frequency, and monetary variables, often referred as RFM model, are given by Shihab et al (2019); Abdulhafedh (2021); Aktaş et al (2021); and Christy et al (2021). In addition to an application of K-Means and Ward, Abdulhafedh (2021) utilizes a Principal Component Analysis and Aktaş et al (2021) also include GMMs and Spectral Clustering in their benchmarking.…”

Section: State-of-the-art Approaches and Methods In Customer Segmenta...mentioning

confidence: 99%

Improving customer segmentation via classification of key accounts as outliers

Spoor

2022

J Market Anal

View full text Add to dashboard Cite

Customer segmentation and key account management are important use cases for clustering algorithms. Here, a data set of a Portuguese wholesaler for food and household supplies is used as an exemplary application. To increase the quality of the analysis, a two-stage approach is proposed. First, key accounts are filtered by a density-based outlier detection. Second, a Gaussian Mixture Model (GMM) is applied to cluster smaller customers. This two-stage approach is aligned with the business implications of key accounts as outstanding and very differently behaving customers as well as with the core idea of an ABC analysis. Also, the exclusion of key accounts corresponds to the definition of outliers as the results of a different underlying mechanism. Using this two-stage approach shows better clustering results compared to using a one-stage approach applying only a GMM. Therefore, it is concluded that density-based detection of key accounts followed by a clustering using a GMM is beneficial for customer segmentation within B2B applications.

show abstract

Section: State-of-the-art Approaches and Methods In Customer Segmenta...mentioning

confidence: 99%

Improving customer segmentation via classification of key accounts as outliers

Spoor

2022

J Market Anal

View full text Add to dashboard Cite

show abstract

“…Penggunaan algoritma clustering sudah pernah dilakukan pada penelitian-penelitian sebelumnya, yaitu penggunaan sistem clustering untuk memudahkan proses identifikasi bahan menu makanan halal (Sucipto et al, 2021) (Fitriana et al, 2017); Penerapan sistem intelijensia bisnis yang dipadukan dengan metode K-Means pada bagian pemasaran di pabrik roti (Fitriana et al, 2018); Segmentasi pelanggan dilakukan menggunakan algoritma clustering untuk menganalisis perilaku pelanggan dan mengelompokkannya (Aryuni et al, 2018;Maryani et al, 2018;Shihab et al, 2019;Syakur et al, 2017); Pemanfaatan clustering untuk mengelompokkan berbagai jenis pekerjaan yang diminati oleh pencari kerja menggunakan K-Means clustering (Shamrat et al, 2020); Perbandingan validasi algoritma K-Medoids dengan K-Means dengan menggunakan Silhoutte Coefficient Index dalam mengelompokkan wilayah cacat pada anak (Marlina et al, 2018); Perbandingan atara algoritma K-Medoids dan algoritma K-Means untuk pengelompokan menu masakan bahan-bahan dari ikan dengan pemilihan algoritma terbaik berdasarkan nilai Davies Bouldin Index (Suarna et al, 2021); Analisis komparatif K-Means dengan K-Medoids dari kedua algoritma dalam kelompok data yang berbeda untuk menjelaskan kekuatan dan kelemahan keduanya (Arbin et al, 2015); Evaluasi kinerja algoritma K-Means dasar dilakukan dengan menggunakan berbagai distance metrics (Thakare dan Bagal, 2015); Peningkatan hasil clustering berdasarkan Davies Bouldin Index dalam menentukan centroid awal pada algoritma K-Means (Sitompul et al, 2019).…”

Section: Abstrakunclassified

Implementasi K-Means Dan K-Medoids Dalam Pengelompokan Wilayah Potensial Produksi Daging Ayam

2022

j.tek.ind.pert

View full text Add to dashboard Cite

Livestock is the main sector in the effort to fulfill food needs for people in Indonesia and has the potential to maintain the availability of animal food. Guidance and socialization to provide information and knowledge in the field of food production from animals, especially in areas with low levels of chicken meat production need to be done. The research objectives were the use of the K-Means and K-Medoids algorithms for grouping chicken meat production areas in the province of West Java and the use of the Davies Bouldin Index (DBI) value in choosing the best algorithm. The application of K-Means and K-Medoids was carried out through the data mining process phase, namely data collection, data preprocessing, data mining implementation, evaluation of the number of clusters, determination of the best algorithm, and clustering results. The K-Means algorithm with 5 clusters can optimally classify potential areas for chicken meat production in West Java province with a DBI value of 0.273. The results of clustering can be used in business processes related to information on the amount of chicken meat production in the West Java region as a reference in the pattern of guidance to increase animal food production, develop chicken farming potential, and develop animal feed distribution potential.

show abstract

“…The resulting two groups were categorized based on frequency and the target customers would be offered some special offers to achieve the marketing goals of the organization [5]. An analysis with agglomerative, K-means and an advanced version of K-means clustering were carried out for RFM based market segmentation approach in [6]. Although aimed at direct marketing, Mohammad Amini et al proposed a classification method which removes the imbalance of data using a combination of clustering and under-sampling.…”

Section: Introductionmentioning

confidence: 99%

Customer Behavior Clustering Based on Balance History Using Dynamic Time Warping Distance

Hung¹,

Dat²

2020

IJMLC

View full text Add to dashboard Cite

Customer clustering, the division of customers into different groups, is a classical problem. It is especially important in banking as it serves multiple purposes in marketing, risk management, etc. Therefore, it has attracted the use of many modern machine learning models and techniques. But currently, most of them are only making use of "static" customer information. This paper proposes a new approach for customer clustering in banking based on the customers' balance history. Basic Dynamic Time Warping (DTW) distance and Soft-DTW (SDTW) distance, an advanced form, are used to measure the difference between customers. To which, the two most popular strategies in time series clustering strategies, partitional and hierarchical, are applied which. In additional, some statistical features are given to prove the effectiveness of the proposed method.

show abstract

RFM Based Market Segmentation Approach Using Advanced K-means and Agglomerative Clustering: A Comparative Study

Cited by 22 publications

References 11 publications

Improving customer segmentation via classification of key accounts as outliers

Improving customer segmentation via classification of key accounts as outliers

Implementasi K-Means Dan K-Medoids Dalam Pengelompokan Wilayah Potensial Produksi Daging Ayam

Customer Behavior Clustering Based on Balance History Using Dynamic Time Warping Distance

Contact Info

Product

Resources

About