About Karpiu

Karpiu is a package designed for marketing mix modeling by calling Orbit from the backend. Karpiu is still in its beta version. Please use it at your own risk.

Installation

To access the development version, please follow the below instructions or simply use make install-dev after cloning the repository. The package only supports`orbit>=1.1.4 which requires cmdstanpy.

$ git clone https://github.com/edwinnglabs/karpiu.git
$ cd karpiu
$ pip install cmdstanpy
$ pip install -r requirements.txt
# required by mkdocs
$ pip install poetry
$ pip install -r requirements-test.txt
$ pip install -r requirements-docs.txt
$ pip install -e .

Related Work

Codebase

1. Roby - Robyn is an automated Marketing Mix Modeling (MMM) code. It aims to reduce human bias by means of ridge regression and evolutionary algorithms, enables actionable decision making providing a budget allocator and diminishing returns curves and allows ground-truth calibration to account for causation.

2. lightweight_mmm - LMMM is a python library that helps organisations understand and optimise marketing spend across media channels.

Research

• Jin, Y., Wang, Y., Sun, Y., Chan, D., & Koehler, J. (2017). Bayesian Methods for Media Mix Modeling with Carryover and Shape Effects. Google Inc.
• Chan, D., & Perry, M. (2017). Challenges and Opportunities in Media Mix Modeling.
• Sun, Y., Wang, Y., Jin, Y., Chan, D., & Koehler, J. (2017). Geo-level Bayesian Hierarchical Media Mix Modeling.

Community Articles

• Are Marketing Mix Models Useful? I Spent My Own Money To Find Out by Mario Filho.
• How Google LightweightMMM Works by Mike Taylor.
• Bayesian Media Mix Modeling for Marketing Optimization by Benjamin Vincent.

Fun Fact

Karpiu is a term invented the author's daugther while she just reached her terrible two. In the early development of this project, "Karpiu" became the dominating term in the author's home office. The author later dedicated this term to the package.