The in-house marketing attribution solution
$ pip install --upgrade setuptools
$ pip install ChannelAttribution
Is Channel Attribution Pro right for you?
- You want to develop accurate, scalable models to measure the impact of marketing investments.
- You don't want to use an expensive black box solutions which lacks transparency and cannot be customized to your needs.
- You don't have time or lack expertise to build marketing measurement models from scratch.
- You want guidance from expert Data Scientists who have years of experience in tackling marketing measurement problems.
Introducing Channel Attribution Pro
Use our tried and tested models to accurately measure the impact of your marketing investments.
Tune your models to the unique needs of your business model and data model.
Run your models on massive data sets leveraging our efficient parallel processing algorithms.
- Multi-Touch Attribution - Model user touch points to understand marketing channel contribution.
- Incrementality Measurement - Model incrementality to measure the impact of marketing experiments.
- Marketing Mix Model - Model channel mix to understand contribution where user data is missing.
|Open Source Version||ChannelAttribution Pro|
|Models||Channel Level Multi-Touch Attribution|
|Transaction Level Multi-Touch Attribution|
|Lift Experiment Measurement|
|Marketing Mixture model|
|Data cleaning and Exploration|
|Other||Access to the Marketing Measurement Handbook|
|Provide input on the ChannelAttribution dev roadmap|
|Marketing Measurement Workshops|
“ChannelAttribution Pro is a cornerstone of our marketing measurement strategy. The methodology came up from an intense collaboration with the ChannelAttribution team. As far as we know, it is an industry breakthrough.”
Senior Data Analyst, Get Your Guide
“We are using ChannelAttribution Pro to create automated reports on campaign level marketing performance. This already gives us a much better understanding of the performance of certain channels (for example Display and App Acquisition channels) than what we had with more simplistic (heuristic) attribution models.”
Marketing Technology Lead, Albelli
“By leveraging a data-driven attribution model we have eliminated the biases associated with traditional attribution mechanisms. We have been able to understand how various messages influence our potential customers and the variances by geography and revenue type.”
Principal Data Scientist, Cloudera
“Markov chains can be a pain to implement (especially at scale), but luckily for us, the “ChannelAttribution” R package written by Davide Altomare and David Loris makes this a lot easier.”
Group Product Manager, Adobe Analytics