Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Krisnadana
I Putu Noven Hartawan
Program Studi Bisnis Digital, Institut Bisnis Dan Teknologi Indonesia, Denpasar, Bali, Indonesia
Computer Science & IT Control & Systems Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Customer Segmentation Using RFM Model and Fuzzy C-Means at PT SNS 21 Bali I Made Dwi Putra Asana; Made Leo Radhitya; Dewa Nyoman Yogantara; I Gede Sudiantara; I Putu Noven Hartawan
Jurnal Krisnadana Vol 5 No 1 (2025): Jurnal Krisnadana- in Progress September-October 2025
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i1.929

Abstract

This study aims to develop an effective customer segmentation model for PT Sukses Nusantara Sakti 21 Bali, a large-scale multi-level marketing distributor with over 60,000 members. The proposed approach integrates the Recency, Frequency, Monetary (RFM) model with the Fuzzy C-Means (FCM) algorithm to analyze one year of sales transaction data. The CRISP-DM framework was adopted to ensure a structured process, consisting of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Customer transaction records were preprocessed to compute normalized RFM scores, which were then clustered using FCM to capture overlapping membership patterns and better reflect behavioral diversity. The segmentation results were validated using the Silhouette Coefficient and Davies–Bouldin Index, achieving scores of 0.6005 and 0.5093, respectively, indicating high-quality cluster compactness and separation. Three distinct customer segments were identified, each providing actionable insights for targeted marketing strategies, including retention, engagement, and reactivation programs. The findings confirm that integrating RFM and FCM offers a robust and flexible approach for customer segmentation in large-scale MLM contexts. Future work may involve real-time segmentation and integration with predictive analytics to further enhance marketing decision-making.
Hyperparameter Analysis of an LSTM Model for Product Sales Forecasting I Putu Noven Hartawan; I Gede Sudiantara; I Dewa Putu Gede Wiyata Putra; Ayu Gede Willdahlia; I Made Dwi Putra Asana
Jurnal Krisnadana Vol 5 No 1 (2025): Jurnal Krisnadana- in Progress September-October 2025
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i1.952

Abstract

We study monthly retail demand forecasting with an LSTM using a large real-world transaction history. The model is trained on historical monthly aggregates and evaluated on a two-month held-out horizon (January–February 2022) across 450 items. To avoid conflating optimization with forecasting performance, we report test-set accuracy using RMSE and MAPE, while training/validation losses are used only for model selection via early stopping. We run a controlled sweep over learning rate, batch size, and hidden units and find that the learning rate primarily drives convergence and accuracy, whereas the other two hyperparameters are secondary under our configuration. We also document practical data-preparation choices (outlier handling and chronological splitting) common in retail deployments. The study is framed as a single-customer case to ensure a consistent assortment and complete history; we therefore discuss external validity and reproducibility guidance. These findings help practitioners prioritize hyperparameter-tuning effort and set realistic expectations for short-horizon monthly demand forecasting in operational settings
Co-Authors Ayu Gede Willdahlia Dewa Nyoman Yogantara I Dewa Putu Gede Wiyata Putra I Gede Sudiantara I Made Dwi Putra Asana Made Leo Radhitya