You are here:
Maximize Win Rate Model Template
Explore the key drivers for winning deals without the hassle of prepping your data.
Note Einstein Discovery stories are now models. We wish we could snap our fingers to update
the name everywhere, but you can expect to see the previous name in a few places until we
replace it.
This article describes the app and associated assets that Einstein Discovery generates when you create a model using the Maximize Win Rate model template.
Use Case
Prerequisites
Einstein Discovery checks your org to determine whether it meets the requirements to generate an app from this template.
| Check for | What's Required |
|---|---|
| Minimum requirements | At least 400 closed opportunities with Amounts greater than 0. |
| Optional objects |
|
| Field access | The logged-in user has access to all the fields needed to build an app from the template. |
| Salesforce configuration | Org uses Record Types. |
| Data | 400 closed opportunities within the past three years (up to 1095 days). |
Generated Assets
Einstein Discovery generates an app containing the following assets.
| Asset Type | Default Name | Description |
|---|---|---|
| Model | Maximize Win Rate | Explains the driving factors for maximizing the likelihood for an opportunity to win as well as recommendations on how to improve the outcome. The initial model focuses on fields that provide good predictive signals and avoids obvious data leakage. |
| CRM Analytics Dataset | Opportunity Win Rate Training Dataset | Dataset used to train the machine learning model. |
| CRM Analytics Data Prep Recipe | appName_recipe | Data Prep recipe that pulls relevant account information from Salesforce to generate a dataset that is used to train a machine learning model. Design is based on best practice feature engineering and data filters. |
| Dashboard | About This Story |
|
| Prediction Definition, Model | Predicted Likelihood to Win, IsWon | Deployed automatically. |
Salesforce Objects
- Account
- Opportunity
- Opportunity History
- Product
- Price Book
- Task
- Event
- User
- UserRole
Model Outcome Variable and Derived Variables
The generated dataset includes the following data. For a complete list, refer to the dataset or model.
| Variable Name | Data Type | Description |
|---|---|---|
| Won (outcome) | text | Model goal is to maximize Won (true). |
| # Amount Decreased | numeric | The number of times the opportunity Amount was decreased. |
| # Amount Increased | numeric | The number of times the opportunity Amount was increased before it was closed. |
| # Closed Date Pushed | numeric | The number of times the closed date was pushed out on the opportunity before it closed. |
| # Completed Activities | numeric | The number of completed activities on the opportunity. |
| # Lost Opportunities on Account | numeric | The number of closed lost opportunities associated with an account. |
| # Won Opportunities on Account | numeric | The number of closed won opportunities associated with an account. |
| Account Tenure | numeric | How long the account record has lived in Salesforce. Calculation: (Today - Account Created Date). |
| Top Product Family | text | Top product family associated with each opportunity based on the opportunity line item with the largest total price. |
| Top Product Name | text | Top product associated with each opportunity based on the opportunity line item with the largest total price. |
Did this article solve your issue?
Let us know so we can improve!
