About Yotpo’s Predictive Analytics

Overview

Yotpo uses machine learning techniques to analyze all of your customer data and predict future customer behavior. Predictive data points are actionable insights that reveal valuable engagement opportunities that significantly improve both short-term engagement and long-term brand loyalty. This guide covers the different types of predictive data points, the algorithms Yotpo uses to compute this data, and how you can utilize this data.

Prerequisites

To benefit from predictive data, you’ll need:

• At least 6 months of valid order history
• At least 500 customers who made a purchase more than 3 months ago
• An eCommerce integration with Shopify, BigCommerce, Adobe Commerce (Magento), or an integration that syncs orders via our Core API

Likely to Purchase and Churn Risk data points

Likely to Purchase and Churn Risk are 2 predictive data points that can be used to segment within Lists & Segments. The Likely to Purchase data point predicts the likelihood of a consumer making a purchase within the next 90 days. The Churn Risk data point gives the likelihood a consumer will churn within the next 90 days.

The score is based on machine learning models that are trained specifically for your store. This means that we build a predictive model that is unique to your brand based on the data that we collect and receive about customers in your store.

How it works

Our models learn from historical purchase data and use it to train models that predict future behavior based on the past purchase events made by each customer. We retrain your model every week to keep it up-to-date with current customer behavior.

Likely to Purchase - what the scores mean

The AI engine studies all of your customers’ purchase behavior, and it assigns each customer a prediction in the form of a score of 0-3. The number is based on the customer’s purchase behavior in relation to the purchase history of all the other shoppers in your store.

• Score = 3 (High): Customers are most likely to make a purchase in the next 90 days (compared to all the other customers in your store)
• Score = 2 (Medium): Customers are relatively likely to make another purchase within the next 90 days (relative to the other customers)
• Score = 1 (Low): Customers are less likely to make another purchase within the next 90 days.
• Score = 0 (Insufficient Data): Displayed if the store does not have enough data history to train an accurate model

Churn Risk - what the scores mean

The AI engine studies all of your customers’ purchase behavior, and it assigns each customer a prediction in the form of a Score of 0-4. The number is based on the customer’s purchase behavior in relation to the purchase history of all the other shoppers in your store.

Score = 4 (Churned): Customers who have not made a purchase in over a year and have most likely churned from your store.

Score = 3 (High): Customers are most likely to churn in the next 90 days (compared to all the other customers in your store)

Score = 2 (Medium): Customers are relatively likely to churn within the next 90 days (relative to the other customers)

Score = 1 (Low): Customers are less likely to churn within the next 90 daysScore = 0 (Insufficient Data): Displayed if the store does not have enough data history to train an accurate model