Recommendation systems have been around us for quite some time now. Youtube, Facebook, Amazon, and many others provide some sort of recommendations to their users. This not only helps them show relevant products to users but also allows them to stand out in front of competitors.
You have a website, similar to medium.com, where users can read content and engage. With Google analytics integrated you can easily answer questions such as the average time on page spent by the user? What are the top pages where the user stays the most and so on? Because Google analytics provides an average time-on-page metric that you can use to answer many of the time-related questions.
But unlike Google Analytics, Mixpanel Analytics doesn’t track any of such metrics. So unfortunately no average time spent metric out of the box.
Fortunately, there is a way around to track time between…
Almost all retargeting efforts, directly or indirectly, focused on one thing and one thing only, make users convert. Easy right? Not Really.
Bringing users to the platform is one thing and making them convert is another. It takes a village to move users across different steps of the funnel towards the final goal. They can drop at any step of the funnel. They land on the website and can bounce immediately, signup, and can drop off, view a product, and may do nothing. What a frustration.
You have implemented Mixpanel analytics on your website and you closely monitor users' activities. This lets you understand users' behavior and allows you to improve your product.
Given Mixpanel’s data model you have to send the event to it to see what’s the users are doing. Unlike Google Analytics, which tracks a lot of things itself even if you don’t send any event, Mixpanel wholly relies on events to produce the insights.
There is no second opinion that the event model for the analytics platform is very strong, in fact, Google also moved to this model with GA4. …
Thinkfic is a platform to make it easy to create, market & sell online courses. Everything you need to run your education business under one roof.
However, one thing it lacks is the ability to track the session duration for each student. You can’t monitor how much time students spent on courses.
We can leverage Mixpanel analytics for this purpose. It allows analyzing user's (students in our case) behavior across your sites with a real-time cohort.
The best part is Thinkfic has direct integration to Mixpanel.
Here is how it will look in the Mixpanel
Capturing data from multiple sources is the key to creating a rich data warehouse. And it becomes even more crucial when it comes to online businesses as the data is scattered across a plethora of platforms used to run the business.
SendGrid is one such marketing platform that delivers transactional and marketing emails to help keep users informed and engaged.
We will go over different methods to store SendGrid email data to our data warehouse tool.
SendGrid provides several ways to export its data out. One such way is to use SendGrid webhooks. Webhooks are automated messages sent from apps…
Cloud SQL is a database service from Google Cloud Platform that makes it easy to set up, maintain, and manage relational databases.
However, It isn’t built for heavy analytics operations. You need a warehouse service such as BigQuery to do advanced analytics and machine learning tasks such as performing RFM analytics using BigQuery ML. For this, you need to move your cloud SQL data to BigQuery.
In this guide, we will build a data pipeline to send the cloud SQL data to BigQuery in an automated fashion.
For our data pipeline, we will make the use of two GCP components
An e-commerce company reached out to you to build a recommender system to suggest three items on their product detail page. Their analytics systems have around 30% of the user’s purchase history and only 20% of the products have users rating history. What method will you use for this type of problem? What will be your evaluation technique?RMSE, Precision, MRR, nDCG, or any other?
In this article, we will build a recommender system for the product detail page to recommend items to users based on their rating history.
We will evaluate Eight different models to get ourselves the best working…
Finding similar products to suggest is a tough nut to crack, especially when we have a large number of products. We want to suggest similar products in our number of marketing and product activities, such as in promotional email marketing.
Here is the super art, I build using autodraw, illustrating a marketing email having suggestions for similar products with the main product.