---
title: "Explainable Predictions"
date: "2024-02-14T06:18:38+00:00"
summary: "Unlock the power of machine learning predictions with our Explainable Predictions feature. Understand customer behavior, design targeted campaigns, and make data-driven decisions by analyzing contributing factors for each profile."
image:
type: "page"
url: "/customer-data-platform/explainable-predictions"
id: "72b8c669-97cf-40b3-ab45-8d5e933cae7a"
---

The Explainable Predictions feature explains the Machine Learning predictions for each customer profile in 360.

By leveraging this feature, marketers can understand the input factors that contribute towards the machine learning prediction made for a given customer profile. Therefore, marketers can understand all the factors that affect an individual’s prediction, and design campaigns that take all such factors into account for individuals with similar demographics.

Marketers can leverage this mechanism for building campaigns where the contributing factors for individuals are used to target specific demographic behavior, which are otherwise opaque to traditional analytics and reporting.

Description and usage
---------------------

To access this feature:

1.  [Sign in to the CDP user interface](/customer-data-platform/getting-started/signin-cdp).
2.  Click **360 Profiles**.
    
    ![Machine learning tab](https://acquia.widen.net/content/qpqdyvqx6o/jpeg/cdp_machine-learning-tab.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
3.  Click the **Machine Learning** tab.
4.  Click **Explain Prediction**.
    
    The system displays a window that explains the positive and negative contribution of the input features to the machine learning prediction of the individual. You can compare these values relative to the baseline prediction or the prediction that does not account for the input factors, and uses the model’s global parameters. You can view the explanation for an individual’s **Likelihood to Buy** prediction. Hovering on each respective bar shows the relevant explanation for each factor.
    
    Note
    
    The **Explain Prediction** option is available for all supervised models such as [Likelihood To Buy](/customer-data-platform/add-on/machine-learning/likelihood-to-buy), [Predictive Lifetime Value](predictive-lifetime-value.html), and [Likelihood To Pay Full Price](likelihood-to-pay-full-price.html). This option is unavailable for unsupervised models such as [Behavior Clusters](/customer-data-platform/add-on/machine-learning/behavior-cluster), [Product Clustering](product-clustering.html), and [Fuzzy Clustering](fuzzy-clustering.html).
    
    ![Explain prediction](https://acquia.widen.net/content/xriog6if8l/jpeg/cdp_explain-prediction-customer-1.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    

In the preceding example, the profile of _Elysee Maunton_ has a predicted **Likelihood to Buy** score of `2 - High`. The positively contributing factors in the graph indicate that:

*   _Elysee_ is 22.95% more _Likely to Buy_ than an average customer because of **Total Transaction Counts over All time**.
*   _Elysee_ is 1.02% more _Likely to Buy_ than an average customer because of **Number of Purchased Products over All Time**.

**Total Transaction Counts over All time** and **Number of Purchased Products over All Time** contributed positively towards boosting the score from average to `2-High`.

**Insight**: This indicates that the user made above-average transactions in the past in terms of the number of transactions and the number of products purchased above an average customer’s engagement levels.

Based on the preceding example and negatively contributing factors, the graph indicates that:

*   _Elysee_ is 8.61% less _Likely to Buy_ than an average customer because of **Number of days since first transaction**.
*   _Elysee_ is 3.89% less _Likely to Buy_ than an average customer because of **Number of transactions in last 30 Days**.

**Number of days since first transaction** and **Number of transactions in last 30 Days** contributed towards reducing the **Likelihood to Buy** score.

**Insight**: The user has above-average engagement with the brand, outside the 30-day time window. However, the recent engagement is on the decline, leading to a slight drop in the **Likelihood to Buy** score.

**Conclusion**: _Elysee_ is an ideal candidate for a discount or bundle campaign. Running a time-bound campaign on such a user can maximize the conversion.

Suggestions and tips
--------------------

To gain accurate and aggregate view of demographic behavior, marketers can:

*   Filter the 360 profiles by a demographic criteria like _City_.
*   Aggregate the contributing factors from a varied selection of profiles to arrive at a conclusion and campaign hypothesis.

For example, for a city _Tacoma_, it is useful to look at the details of multiple profiles to understand how the **Likelihood to Buy** contributing factors vary. In the preceding screenshots, the contributing factors vary for:

*   _Elysee_ with a `2 - High` **Likelihood to Buy** score.
    
    ![Explain prediction](https://acquia.widen.net/content/xriog6if8l/jpeg/cdp_explain-prediction-customer-1.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
    ![Likelihood to buy - score customer](https://acquia.widen.net/content/skywmw5r5k/jpeg/cdp_likelihood-to-buy-score-customer-1.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
*   _Kingsy Beveredge_ with a `4 - Medium` **Likelihood to Buy** score.
    
    ![Explain prediction](https://acquia.widen.net/content/q5r7a1oc57/jpeg/cdp_explain-prediction-customer-2.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
    ![Likelihood to buy - score customer](https://acquia.widen.net/content/36vfec8anu/jpeg/cdp_likelihood-to-buy-score-customer-2.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
*   _Gannon Lourens_ with a `7 - Low` **Likelihood to Buy** score.
    
    ![Explain prediction](https://acquia.widen.net/content/7xdboyyaug/jpeg/cdp_explain-prediction-customer-3.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    
    ![Likelihood to buy - score customer](https://acquia.widen.net/content/ceuu8j6kat/jpeg/cdp_likelihood-to-buy-score-customer-3.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)
    

The three profiles indicate that:

*   _Elysee Maunton_’s `2 - High` **Likelihood to Buy** score is bolstered by higher _Total Transactions Count_ and lower _Number of Days since first transaction_.
*   _Kingsley Bevergede_’s `4 - Medium` **Likelihood to Buy** (lower score compared to _Elysee Maunton_) was brought down by the _Email send since last time_ score, suggesting that the user did not engage on that channel through campaigns, and therefore, lookalikes can be a target for a “Revive” campaign.
*   _Gannon Loure_’s `7 - Low` **Likelihood to Buy** score is slightly bolstered by _Transaction date since first transaction_ (suggesting recent purchase). This suggests that the customer initially made a few purchases but engagement is low subsequently. This can be an ideal case for a discount and re-engage campaign.

Feature dictionary
------------------

It is important to understand the input features that feed a machine learning model. To surface the input parameters and their human readable definitions in CDP, you can leverage the Feature Dictionary feature available in all the machine learning models. These are available in the individual dashboards for all machine learning models.

For example, in the **Likelihood to Buy** ML dashboard, you can scroll down to the **Explainability** section to view the Feature Dictionary tile. This contains the input features for the **Likelihood to Buy** model along with their human readable descriptions.

![Likelihood to buy - feature dictionary](https://acquia.widen.net/content/bb66fqey3o/jpeg/cdp_likelihood-to-buy-feature-dictionary.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)

For the **Likelihood to Convert** model, the Feature Dictionary tile appears as follows:

![Likelihood to convert - feature dictionary](https://acquia.widen.net/content/ndjuys4uka/jpeg/cdp_likelihood-to-convert-feature-dictionary.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)

You can access the same dashboards from **360 Profiles**. To view the dashboard, you must click the **i** button adjacent to the **Input Features** label.

![Explain prediction](https://acquia.widen.net/content/bdpwppihoi/jpeg/cdp_explain-prediction.jpeg?position=c&color=ffffffff&quality=80&u=lcfvma)