station-10 / awesome-marketing-machine-learning

A curated list of awesome machine learning libraries for marketing, including media mix models, multi touch attribution, causal inference and more

awesome-marketing-machine-learning

A curated list of awesome machine learning libraries for marketing. Inspired by both awesome-production-machine-learning and awesome-machine-learning, and created and maintained by Station 10.

Note that some packages could fit into more than one section. This has been noted in the descriptions so be sure to Ctrl + F as well as exploring by sections.

Want to contribute? Please raise a Pull Request or an issue. If you find this useful please drop a ⭐️. This helps motivate us and others to update and maintain the list.

All packages are Python based unless otherwise stated. We welcome contributions from R Users!

Main Content

Attribution

• ChannelAttribution Python and R library that employs a k-order Markov representation to identify structural correlations in customer journey data.
• fractribution Data driven MTA by Google.
• Marketing-Attribution-Models Heuristic and data driven Multi Touch Attribution.
• markov-chain-attribution Leverages a first order Markov chain to reallocate conversions.
• mta Various data driven Multi Touch Attribution algorithms.
• pychattr Python implementation of the excellent R ChannelAttribution library.
• shapley Shapley Values For Attribution Modelling.
• shapley-attribution-model-zhao-naive Shapley Value Methods for Attribution Modeling (Naive, Set-based).

Causal Inference

• CausalImpact (R) Causal Inference using Bayesian structural time-series models by Google.
• causalml Uplift modeling and causal inference with ML by Uber.
• CausalPy Causal Inference & Synthetic Control. Supports fitting with scikit-learn and PyMC models.
• dowhy Causal Inference that supports explicit modeling and testing of causal assumptions.
• SyntheticControlMethods Causal inference using Synthetic Control.
• tfcausalimpact Google's CausalImpact Algorithm implemented on top of TensorFlow Probability.
• upliftml Scalable unconstrained and constrained uplift modeling from experimental data using PySpark and H20.
• scikit-uplift
• Uplift modeling python package that provides fast sklearn-style models implementation, evaluation metrics and visualization tools.

Churn / CLV

• btyd Buy Till You Die and CLV statistical models in Python.
• lifetimes CLV and Churn modelling. Deprecated and incorporated into pymc-marketing.
• lucius-ltv CLV for subscriptions.

Data

• gapandas4 Python package for querying the Google Analytics Data API for GA4 and displaying the results in a Pandas dataframe.

Econometrics

• EconML AI, Econometrics and Causal Inference modelling.
• statsmodels Statistical modeling including time series and econometrics.

Geo Experimentation

• trimmed_match Ad effectiveness through the design and analysis of randomized Geo Experiments by Google.
• matched_markets Time-Based regression matched markets approach for designing Geo Experiments by Google.
• GeoexperimentsResearch (R) Open-source implementation of the geo experiment analysis methodology developed at Google (Archived)
• GeoLift Geo Experimentation methodology based on Synthetic Control Methods used to measure lift of ad campaigns by Facebook.

Media / Marketing Mix Models

• BayesianMMM Bayesian Media Mix mMdelling with shape and carryover effect.
• dammmdatagen (R) Media Mix Modeling Data Generator.
• lightweight-mmm Bayesian Media Mix Models by Google.
• mamimo Small Media Mix Models designed to be used in conjunction with ML libraries (e.g. SKL)
• mmm-stan Multiplicative Media Media Mix Model.
• pymc-marketing Bayesian Media Mix, Adstock, Saturation Customer Lifetime Value & Churn models.
• Robyn (R) Bayesian Media Mix Models by Facebook.

Personalisation / Segmentation

• amazon-denseclus Python module for clustering both categorical and numerical data using UMAP and HDBSCAN by Amazon.
• rfm RFM Analysis and Customer Segmentation.
• retentioneering-tools Retentioneering: product analytics, data-driven customer journey map optimization, marketing analytics, web analytics, transaction analytics, graph visualization, and behavioral segmentation
• ecommercetools Data science toolkit for those working in technical ecommerce, marketing science, and technical seo and includes a wide range of features to aid analysis and model building.

Recommendation Systems

• lightfm Implementation of LightFM, a hybrid recommendation algorithm.
• openrec Open-source and modular library for neural network-inspired recommendation algorithms.
• recmetrics A library of metrics for evaluating recommender systems
• recommenders Best Practices on Recommendation Systems by Microsoft.
• Surprise Scikit for building and analyzing recommender systems that deal with explicit rating data.

Time Series

• darts Python library for user-friendly forecasting and anomaly detection on time series built using SKL conventions.
• gluonts Probabilistic time series modeling, focusing on deep learning based models, based on PyTorch and MXNet.
• neural_prophet Framework for interpretable time series forecasting built on PyTorch.
• orbit Python package for Bayesian time series forecasting and inference by Uber.
• pmdarima
• Pmdarima is a statistical library designed to fill the void in Python's time series analysis capabilities.
• prophet Additive time series modelling by Facebook.
• sktime A unified framework for ML with Time Eeries.
• statsforecast Lightning ⚡️ fast forecasting with statistical and econometric models.
• stumpy STUMPY computes something called the matrix profile, which is just an academic way of saying "for every subsequence automatically identify its corresponding nearest-neighbor"
• temporian Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖.
• tbats BATS and TBATS time series forecasting
• tsfresh Time Series Feature extraction based on scalable hypothesis tests.
• tslearn The machine learning toolkit for time series analysis in Python.

Survival Analysis

• lifelines lifelines is a pure Python implementation of the best parts of survival analysis.
• pysurvival An open source python package for Survival Analysis modeling.
• scikit-survival Survival analysis built on top of scikit-learn.

Synthetic Control

• pysyncon Multiple Synthetic Control implementations.
• scpi Provides Python, R and Stata implementations of estimation and inference procedures for synthetic control methods.
• SparseSC Sparse Synthetic Control Models in Python by Microsoft.

Synthetic Data

• Decoy Synthetic Data Generator using DuckDB at its core.
• SDV Python library designed to be your one-stop shop for creating tabular synthetic data.