PyMC Labs is excited to announce the initial release of PyMC-Marketing
PyMC Labs is excited to announce the initial release of PyMC-Marketing. Unlock the power of marketing analytics with PyMC-Marketing – the open source solution for smarter decision-making. Media mix modelling and customer lifetime value modules allow businesses to make data-driven decisions about their marketing campaigns. Optimize your marketing strategy and unlock the full potential of your customer data.
PyMC-Marketing provides a user-friendly API for working with two key types of models: Media Mix Models (MMM) and Customer Lifetime Value (CLV). Although MMM and CLV are often treated separately, we believe that employing them side-by-side can provide a more complete picture on the short- and long-run return on investment of marketing activities.
Since the death of the cookie, it has become very hard, if not impossible to attribute any single sale (or user signup) to a particular advertising channel. You may be spending on various advertising channels like linear TV, different social medias, radio, print etc. But how can you evaluate the effectiveness of these channels in order to intelligently allocate future advertising budgets? This is the goal of Media Mix Models.
When used correctly, MMMs can evaluate channel effectiveness, differentiate changes due to advertising spend, holidays, seasonal trends, or macro-economic factors. Models like this account for the diminishing returns of ad exposure over time, and channel saturation.
📖 Find out more about Bayesian MMMs in our blog post Bayesian Media Mix Modeling for Marketing Optimization.
PyMC-Marketing focuses on ease-of-use, so it has a simple API which allows you to specify your outcome (e.g. user signups or sales volume), historical advertising spend data, and control variables such as holidays or seasonality:
➡️ Find out more about how to use MMMs to analyze your data in our Example Notebooks documentation.
Let's say that you have embraced MMMs and are working towards maximizing new user signups. This is all well and good, but what you really want to do is to acquire more high value customers. But how do you know how valuable different customers are likely to be? You don't know what future business they will generate because it's in the future!
This is where Customer Lifetime Value (CLV) models come in. They are used to predict future purchases and to quantify the long-term value of a customer. PyMC-Marketing's Customer Lifetime Value module includes a range of models, to predict future churn rates, purchase frequency and monetary value of customers.
Again, we have a simple API for Customer Lifetime Value modeling. The example below uses a Beta Geometric (aka BG/NBD) model and we specify customer ID, date of each customer’s first and last purchases as well as number of repeat purchases from each customer.
➡️ Find out more about how to use CLV models and the current features in our Example Notebooks documentation.
In recent years, there has been a significant shift across many data-intensive industries to build upon open source foundations. There are several advantages in building your marketing data science stack on an open source core:
Unlock your potential with a free 30-minute strategy session with our PyMC experts. Discover how open source solutions and pymc-marketing can elevate your media-mix models and customer lifetime value analyses. Boost your career and organization by making smarter, data-driven decisions. Don't wait—claim your complimentary session today and lead the way in marketing and data science innovation.
We are on a journey to make Bayesian Media Mix and Customer Lifetime Value models more accessible and user-friendly to the marketing community.
PyMC-Marketing is still in its early stages of development, and we welcome feedback and contributions from the community. Visit our PyMC-Marketing GitHub repository and get involved!
Stay tuned for more information here on the PyMC Labs blog, sign up to our newsletter, follow us on Twitter and LinkedIn, its members, and the PyMC-Marketing contributors.
And check out the package here where you'll find more details, including installation instructions:
If you are interested in seeing what we at PyMC Labs can do for you, then please email email@example.com. We work with companies at a variety of scales and with varying levels of existing modeling capacity. We also run corporate workshop training events and can provide sessions ranging from introduction to Bayes to more advanced topics.