You are here:
Solution Implementation Tasks
The process of implementing Einstein Discovery solutions typically involves a series of tasks.
Common Tasks
| # | Task | Description | More Information |
|---|---|---|---|
| 1 | Define the Outcome | Define an outcome that you want to improve. It’s most likely a key performance indicator (KPI) for your business. Most organizations have many outcomes that are candidates for improvement. Start with one outcome that is particularly significant. Over time, you can develop and apply Einstein Discovery to many different outcomes concurrently. | Define Your Target Outcome |
| 2 | Assemble the Data | Design and populate the CRM Analytics dataset to contain the data you want to investigate. A dataset contains tabular data that you normalize for analysis. You can use Salesforce data as well as data that is external to Salesforce. | Integrate Your Data in CRM Analytics |
| 3 | Create the Model | Based on that dataset, create and configure a model that tells Einstein how to analyze your data. Models provide the settings and preferences that Einstein Discovery uses to generate insights. | Create and Manage Models |
| 4 | Investigate Insights | Investigate the insights that Einstein generated during its analysis. Learn what patterns and statistical insights Einstein discovered in your data. | Explore Data Insights |
| 5 | Evaluate Model Quality | Assess performance and refine the predictive model. | Evaluate Model Quality |
| 6 | Deploy the Model | Deploy the model into Salesforce. | Deploy Models |
| 7 | Predict and Improve Outcomes |
Predict outcomes and get improvements using the model you deployed. | Predict & Improve Outcomes |
Iterative Refinement and Continuous Improvement
Implementation is an iterative process rather than a linear one. Einstein Discovery is designed for rapid exploration, experimentation, and implementation. You learn as you go. Every step of the way, you use built-in feedback to check your results, review your assumptions, ask new questions, make adjustments, and try again. Add a column to your dataset. Change model settings. Resolve alerts, refine thresholds, and segment data. As you fine-tune your approach, each improvement can help lead you to better operational outcomes.
