Version: 0.9.8.1
The library generates visualisations to help interpret analysis results, particularly for impact analysis and change point detection. This guide explains how to read and interpret plot types, including correlation risk context when CPC and CTR move inversely.
Generates enhanced two-panel plots for each metric (CPC or CTR) with detailed analytical overlays.
Displays primary metric over time with key analytical overlays:
Shows actual metric values over analysis period
Connected points indicate daily performance measurements
Fluctuations reveal natural variation and trend changes
Horizontal line representing calculated benchmark value
Derived from period of optimal stable performance
Serves as reference point for impact calculations
Indicates time period used to establish benchmark
Typically represents longest stable or improving performance segment
Provides visual context for benchmark derivation
Text annotations showing identified trend classifications
“STABLE” indicates periods of consistent performance
“DECLINING” marks periods where performance deteriorates
“IMPROVING” shows periods of performance enhancement
Based on signature-based change point detection
Highlight periods where actual performance falls below benchmark
Only shown for declining periods after benchmark period ends
Area size reflects magnitude of impact (e.g., engagement gap)
Vertical red lines mark boundaries of impact periods
Mark significant pattern changes detected by signature analysis
Indicate transitions between different performance phases
Based on mathematical signature distance calculations
Shows sophisticated mathematical analysis underlying change point detection:
Each point represents mathematical “distance” between consecutive time windows
Higher values indicate greater changes in underlying pattern
Based on rough path theory and signature calculations
Provides quantitative measure of pattern evolution
Threshold value for anomaly detection
When signature distances exceed this threshold, significant changes are flagged
Automatically calculated based on data characteristics and statistical properties
Mark time points where signature distances exceeded threshold
Correspond to change points shown in top panel
Indicate statistically significant pattern shifts
Enable precise timing of performance transitions
For detailed analysis, generates a four-panel dashboard summarising impact with separate operational (clicks) and financial (GBP) indicators.
Mirrors individual CPC analysis with:
CPC time series with benchmark line and impact highlighting
Segment trend classifications
Change point markers
Underperformance area visualisation
Mirrors individual CTR analysis with:
CTR time series with benchmark line and impact highlighting
Segment trend classifications
Change point markers
Underperformance area visualisation
engagement_gap_clicks (primary): Lost clicks relative to benchmark (operational)
actual_overspend_gbp (secondary): Actual overspend relative to benchmark (financial)
Do not add or combine these metrics; they are conceptually distinct
Impact Metrics
engagement_gap_clicks (primary)
actual_overspend_gbp (secondary, clearly labelled as reference value)
Lost clicks due to CTR underperformance (as engagement gap)
Absolute and relative impact measurements (reported separately)
Benchmark Information
CPC and CTR benchmark values with calculation periods
Provides context for impact calculations
Shows the performance standards used for comparison
Calculation Status
Indicates whether impact calculations were successful
“Success” confirms reliable benchmark establishment
“Insufficient Data” or “No Declining Periods” indicate limitations
Helps assess reliability of results
Analysis Coverage and Exclusions
Analysis Coverage %: Proportion of creatives successfully analysed
Exclusions Summary: Reasons and counts for excluded creatives
Correlation Risk Indicator
Colour-coded severity levels when CPC and CTR move in opposite directions:
Low Risk (Green): Weak or positive correlation
Medium Risk (Orange): Moderate negative correlation
High Risk (Red): Strong negative correlation
Unknown Risk (Grey): Insufficient data for correlation analysis
Metrics are not combined; interpret engagement_gap_clicks and actual_overspend_gbp separately regardless of risk level
Large red shaded areas in time series plots
Substantial gaps between actual performance and benchmark lines
High engagement_gap_clicks and/or notable actual_overspend_gbp magnitudes
Extended periods of declining performance
Small or absent red shaded areas
Performance lines close to benchmark levels
Low engagement_gap_clicks and minimal actual_overspend_gbp in summary panel
Brief or infrequent declining periods
Strong negative correlation between CPC and CTR (r < -0.7)
When CTR declines, CPC often increases proportionally
Do not compute any combined total; interpret each metric separately
Weak or positive correlation between CPC and CTR (r > -0.3)
Independent variation in both metrics
Use engagement_gap_clicks and actual_overspend_gbp independently; do not add
Signature distances fluctuating below the threshold
Indicates natural performance variation without significant pattern changes
Suggests stable underlying performance dynamics
Signature distances exceeding the threshold
Indicates fundamental shifts in performance patterns
May correspond to external factors or creative fatigue
Requires investigation and potential intervention
Clusters of high signature distances
Suggests periods of instability or transition
May indicate gradual performance degradation
Useful for predicting future performance issues
Focus intervention efforts on periods with large underperformance areas
Address the metric contributing most to operational or financial impact
Consider creative refresh at detected change points
Use signature distance trends for proactive management
Use actual_overspend_gbp for financial inefficiency assessment
Use engagement_gap_clicks for operational impact assessment
Do not compute or use any combined total
Plan intervention timing based on trend segment analysis
Allocate resources based on the magnitude and persistence of each metric separately
Monitor signature distances for early warning of performance changes
Set alerts when distances approach detection thresholds
Use benchmark periods as performance targets for optimisation
Implement automated responses to significant pattern changes
Evaluate creative lifecycle based on engagement_gap_clicks and actual_overspend_gbp patterns
Compare performance across different creative assets
Identify optimal refresh timing to minimise impact
Assess ROI of performance optimisation interventions
Sufficient data points for reliable signature calculation
Consistent measurement methodology across time periods
Adequate baseline period for benchmark establishment
Regular data collection without significant gaps
Signature analysis requires minimum window sizes
Benchmark calculations need stable performance periods
Correlation analysis requires sufficient data points
Risk assessments depend on data quality and completeness
External factors may influence performance patterns
Seasonal effects should be considered in analysis
Market conditions may affect benchmark relevance
Multiple testing considerations for change point detection
This visualisation guide provides the foundation for understanding and interpreting CreativeDynamics analysis results, enabling data-driven decision-making in performance marketing contexts.
CreativeDynamics Documentation (Version 0.9.8.1)