Salesforce Marketing Cloud is one of one of the most commonly used Customer Relationship Management (CRM) solutions. The right CRM tool will allow your sales and marketing teams to optimize their workflows and better equip them to maximize your company’s customer- acquisition and engagement strategies.
However, to fully utilize the resource that is your CRM tool you’ll want to allow your teams to leverage your internal data.
In this article we’ll go through how you could set up the Python framework for importing your data to your Salesforce Marketing Cloud platform using their REST API endpoints. …
Web scraping simply means to automatically gather information/data from a website.
This can be extremely valuable both for an experienced data scientist wanting to add new dimensions to an existing dataset, but also for an inexperienced data scientist in search of interesting datasets to start building their portfolio of projects.
In this short article, we’ll go through a simple example of how to write a Python script to automate turning information on a website into a dataset ready for your data science project.
It’s worth mentioning that even though information/data is available online it’s not necessarily legal to use it for commercial purposes — check with the website you intend to scrape before you do so. …
Markov chains, in the context of channel attribution, gives us a framework to statistically model user journeys and how each channel factors into the users traveling from one channel to another to eventually convert (or not). By using these transition probabilities, we can identify the statistical impact a single channel has on our total conversions.
For more details on marketing attribution and Markov Chains, see part 1.
In part 1 on this subject, we covered what marketing attribution is, why accurate and correct attribution is increasingly important and how the theory behind Markov Chains can be applied to this domain.
While that article contained a practical example of how to programmatically apply Markov Chains to an example customer data set in Python, it also involved a heavy dependency on the R package ChannelAttribution. …
In part 1 of this walkthrough we went over the basic building blocks to creating your own successful marketing mix model (MMM). But what makes your MMM successful? You can iterate on the model until the end of time and end up with a model that’s able to perfectly describe reality, but that doesn’t necessarily translate to a successful model.
Since the motivation for putting together your MMM likely is to utilize your historical data to drive real business value, the extent to which your MMM allows you to do so is what defines the success of it.
In this part of the walkthrough we’ll touch on how to effectively use the output of your model to fuel decisions that’ll grow your business. …
In part 1 of this walkthrough on how to build your own Marketing Mix Model we’ll touch on:
In part 2 we’ll get into use cases from the output and wrap up the walkthrough by touching on:
With the number of marketing channels through which we can reach new potential clients increasing every year, it’s more important than ever to have an understanding of which channels are driving the business forward and which are not.
“Half the money I spend on advertising is wasted; the trouble is I don’t know which half.” …
Any business that’s actively running marketing campaigns should be interested in identifying what marketing channels drive the actual conversions. It is no secret that the return on investment (ROI) on your marketing efforts is a crucial KPI.
In this article we’re going to cover: