Toggle Side Panel
Close search
Back to Course

Get Smart with Salesforce Einstein

0% Complete
0/0 Steps

  1. Salesforce Einstein Basics

    Get Started with Einstein
  2. Get Started with Einstein
    7 Topics
  3. Learn About Einstein Out-Of-The-Box Applications
    7 Topics
  4. Responsible Creation of Artificial Intelligence
    Use the Einstein Platform
    9 Topics
  5. Understand the Ethical Use of Technology
    8 Topics
  6. Learn the Basics of Artificial Intelligence
    5 Topics
  7. Recognize Bias in Artificial Intelligence
    6 Topics
  8. Einstein Bots Basics
    Remove Bias from Your Data and Algorithms
    6 Topics
  9. Learn About Einstein Bots
    6 Topics
  10. Plan Your Bot Content
    4 Topics
  11. Einstein Next Best Action
    Learn the Prerequisites and Enable Einstein Bots
    3 Topics
  12. Get Started with Einstein Next Best Action
    9 Topics
  13. Sales Cloud Einstein
    Understand How Einstein Next Best Action Works
    7 Topics
  14. Increase Sales Productivity
    5 Topics
  15. Automate Sales Activities
    5 Topics
  16. Target the Best Leads
    3 Topics
  17. Close More Deals
    6 Topics
  18. Connect with Your Customers and Create New Business
    4 Topics
  19. Sales Cloud Einstein Rollout Strategies
    Improve Sales Predictions
    4 Topics
  20. Use AI to Improve Sales
  21. Start with a Plan
  22. Set Goals and Priorities
  23. Get Ready for Einstein
  24. Quick Start: Einstein Prediction Builder
    Start Using Sales Cloud Einstein
  25. Sign Up for an Einstein Prediction Builder Trailhead Playground
  26. Create a Formula Field to Predict
  27. Enrich Your Prediction
  28. Build a Prediction
  29. Quick Start: Einstein Image Classification
    Create a List View for Your Predictions
  30. Get an Einstein Platform Services Account
  31. Get the Code
  32. Create a Remote Site
  33. Create the Apex Classes
  34. Einstein Intent API Basics
    Create the Visualforce Page
  35. Get Started with Einstein Language
  36. Set Up Your Environment
  37. Create the Dataset
  38. Train the Dataset and Create a Model
  39. Put Predictions into Action with Next Best Action
    Use the Model to Make a Prediction
  40. Learn the Basics and Set Up a Custom Playground
  41. Define and Build a Prediction
  42. Customize Your Contact and List Displays
  43. Create Recommendations for Einstein Next Best Action
  44. Create a Next Best Action Strategy
  45. Add Next Best Action to Your Contacts

Participants 106154

Show more
Lesson Progress
0% Complete

As we’ve said before, developing an AI system starts at the level of your training data. You should be scrupulous about addressing data quality issues as early as possible in the process. Make sure to address extremes, duplicates, outliers, and redundancy in Einstein Analytics or other data preparation tools. Check out this Salesforce Help article to learn more about how to optimize data for predictive analytics.

Before you release your models, make sure to run prerelease trials so that your system doesn't make biased predictions or judgments and impact people in the real world. Ensure that they’ve been tested so that they won’t cause harm. You want to be able to account for your product working across different communities so that you don’t get any surprises upon release.

After you release a model, develop a system for periodically checking the data that your algorithms are learning from, and the recommendations your system is making. Think of your data as having a half-life—it won’t work for everyone indefinitely. On the technical side, the more data enters a system, the more an algorithm learns. This can lead the system  to identify and match patterns that those developing the product didn’t foresee or want.

On the social side, cultural values change over time. Your algorithms’ output may no longer suit the value systems of the communities it serves. Two ways you can address these challenges include paid community review processes to correct oversight, and by creating mechanisms in your product for individuals and users to opt out or correct data about themselves. Community review processes should include people from the communities that may be impacted by the algorithmic system you’re developing. You should also hold sessions with the people who will implement, manage, and use the system to meet their organization’s goals. Head over to our UX Research Basics to learn more about methods you can use to conduct community review processes as well as conduct user research to understand the contexts your tool will be used in.