Results of this run
Fuzzy C-Means on Customer Segments (m=2, k=4, m=2) keeps a membership for every row. Fuzzy silhouette is 0.364, fuzzy Calinski-Harabasz is 373.2, fuzzy Davies-Bouldin is 1.165. Held-out segment versus hardened memberships: adjusted Rand 0.794. 0 noise rows out of 200 after defuzzifying. Fuzzy group 0 on Customer Segments holds 44 rows (annual_income 47244.2 / avg_spend 622.1). Fuzzy group 1 on Customer Segments holds 50 rows (annual_income 78401.2 / avg_spend 2953.6). Fuzzy group 2 on Customer Segments holds 58 rows (annual_income 30574.9 / avg_spend 717.2). Fuzzy group 3 on Customer Segments holds 48 rows (annual_income 56102.0 / avg_spend 1659.3). Fuzzifier path: k 2 soft-assigns 0.591 with 2 groups on Customer Segments; k 3 soft-assigns 0.489 with 3 groups on Customer Segments; k 4 soft-assigns 0.364 with 4 groups on Customer Segments; k 5 soft-assigns 0.247 with 5 groups on Customer Segments; k 6 soft-assigns 0.241 with 6 groups on Customer Segments; k 7 soft-assigns 0.189 with 7 groups on Customer Segments; k 8 soft-assigns 0.140 with 8 groups on Customer Segments. Fuzzy scatter keeps 90.5%.

| k | Silhouette | Clusters |
|---|---|---|
| 2 | 0.591 | 2 |
| 3 | 0.489 | 3 |
| 4 | 0.364 | 4 |
| 5 | 0.247 | 5 |
| 6 | 0.241 | 6 |
| 7 | 0.189 | 7 |
| 8 | 0.140 | 8 |
# Product Fuzzy C-Means: c=4, m=2.0, random_state=42.
# Features are StandardScaler-transformed before the fit.
Who, how, and why
Method: StandardScaler, drop constant columns. Code version 3e4afc4b4352 (scripts/seo/build_explore_artifacts.py). scikit-learn 1.4.2. Seed 42. Dataset source: Synthetic customer records bundled with this site. License: Generated for demos; no external license. The segment column was held out of the fit and used only for the adjusted Rand score.
Results computed on 2026-11-02.
The results paragraph is filled from these numbers by a fixed template in the site code, so the scores can be checked against the same dataset in the tool.
Maintainer: nikolaou1982.
Contact: nick1982100@gmail.com.
