Purpose

Anomalies Detected: 14 weeks (7% anomaly rate) flagged from 200 observations with 100% data retention
Top Anomaly Driver: TikTok spending shows the strongest isolation signal (importance score: 100), indicating it most effectively distinguishes anomalous weeks
Score Separation: Mean anomaly score of 0.568 with minimal separation (0.029) suggests anomalies are subtly different from normal patterns rather than extreme outliers
Feature Patterns: Anomalous weeks show TikTok spending at $0 (vs. $3,168 normal mean), Google Ads elevated to $2,017 (vs. $1,483 normal), and Sales slightly reduced to $9,795 (vs. $10,734 normal)

This section documents the data intake and cleaning phase for the Isolation Forest anomaly detection model. Perfect retention (100%) indicates no rows were removed during preprocessing, meaning all 200 weekly observations of marketing spend across TikTok, Facebook, Google Ads, and Sales proceeded to model training without data loss.

Key Findings

Initial Rows: 200 observations retained without removal
Retention Rate: 100% — no filtering, imputation, or exclusion applied during preprocessing
Train/Test Split: Not applicable for unsupervised anomaly detection; all data used for model fitting
Data Quality Status: No missing values or quality issues detected requiring row removal

Interpretation

The perfect retention rate reflects clean input data with no missing feature values across the four marketing channels. This is favorable for anomaly detection, as Isolation Forest requires complete observations to build isolation trees effectively. The absence of preprocessing transformations (scaling, encoding) suggests features were already in numeric form and suitable for the algorithm without standardization.

Context

Unsupervised models like Isolation Forest don't require train/test splits; instead, all observations contribute to learning the normal spending patterns. The quality checks confirm the dataset met baseline requirements, though this doesn't guarantee the anomalies detected (14 instances) are business-meaningful—only that data integrity was maintained.