How To Compare AMMM With Other MMM Tooling
This page provides a comparison framework for evaluating AMMM against alternative MMM libraries.
Updated: 4 March 2026
Scope and Positioning
Section titled “Scope and Positioning”AMMM is a Bayesian MMM library built on PyMC/PyTensor with optional JAX acceleration, maintained in the WPP/GroupM ecosystem, and designed around a stage-gated diagnostic workflow.
The main differentiator is not a single model form; it is the combination of:
- explicit Bayesian parameterisation,
- workflow-stage artefact governance,
- machine-readable diagnostic outcomes used by downstream reporting.
AMMM V2 Capability Snapshot
Section titled “AMMM V2 Capability Snapshot”| Capability | AMMM V2 status | Notes |
|---|---|---|
| Bayesian inference with posterior uncertainty | Implemented | NUTS-based posterior with 94% HDI reporting. |
| Stage-gated workflow outputs | Implemented | Numbered stage folders 00_... to 80_.... |
| Convergence gate artefact | Implemented | 50_diagnostics/convergence_report.json (converged). |
| Calibration gate artefact | Implemented | 50_diagnostics/calibration_report.json (well_calibrated). |
| Pareto k reliability diagnostics | Implemented | 50_diagnostics/pareto_k_summary.json, pareto_k.png. |
| Prior predictive plausibility checks | Implemented | 10_pre_diagnostics/prior_predictive_*. |
| Response-curve-based optimisation | Implemented | Single-period and multi-period optimisation workflows. |
| Ramp constraints (absolute and percentage) | Implemented | Parsed/validated via parse_and_validate_ramp_constraints. |
| Adstock-aware multi-period objective | Available (advanced) | Implemented, but treated as advanced/experimental in practice. |
| Prophet-assisted baseline option | Implemented | Useful for stability, with documented leakage trade-off. |
| CRE/Mundlak baseline structure | Not in V2 | Roadmap item for V3. |
Practical Comparison Criteria
Section titled “Practical Comparison Criteria”When comparing AMMM with another library, evaluate at least five dimensions:
- Diagnostic governance: are convergence, calibration, and influence diagnostics stage-gated and machine-readable?
- Baseline transparency: is the baseline specification explicit, auditable, and sensitivity-tested?
- Uncertainty treatment: are uncertainty intervals carried through decomposition and decision support?
- Optimisation realism: are constraints (bounds, ramps, multi-period effects) represented explicitly?
- Operational traceability: can stakeholders trace each business output back to diagnostic evidence?
Decision Guidance
Section titled “Decision Guidance”Choose AMMM when you need:
- a disciplined Bayesian workflow with auditable artefacts,
- explicit handling of diagnostic failure modes,
- practical optimisation on top of posterior-informed response curves,
- clear separation between computational adequacy and causal claims.
Choose alternative tooling when your priority is a different ecosystem constraint (for example strict platform integration) and the diagnostic governance model remains acceptable for your risk profile.
Causal Caveat
Section titled “Causal Caveat”No MMM library should be selected solely on predictive fit claims. Strong diagnostics and good fit do not, on their own, establish causal identification.