Sunil Bhardwaj
11 min readDec 13, 2022

Preparatory Notes for The Einstein Prediction Builder Accredited Professional exam : Part 1

Einstein AI Fundamentals

Artificial Intelligence for Business — To use artificial intelligence to meet our business needs.

  1. Technologies that comprise artificial intelligence solutions — The four main ingredients are : yes-and-no predictions, numeric predictions, classifications & recommendations.

Yes-and-No Predictions — Examples: Is this a good lead for my business?” or “Will this prospect open my email?

Yes-and-no predictions generally come in the form of a probability (for example, “Mary Smith has a 67% chance of opening this type of email). But sometimes probabilities are converted into scores. Scores are just a different representation of the likelihood of “yes”; they can be represented as numbers on a numeric scale (for example, 0 to 100) or even as the number of stars on a five-star rating survey. Keep in mind that these scores are just showing the same probability in a different way.

Numeric Predictions — Examples: “How much revenue will this new customer bring in?” or “How many days will it take us to resolve this customer’s issue?”

Classifications — Classifications frequently use “deep learning” capabilities to operate on unstructured data like free text or images. The idea behind classification is to extract useful information from unstructured data & answer questions like, “How many soda cans are in this picture?” It can even take a statement like, “I’d like to buy another pair of the same shoes I bought last time,” & use that to kick off a workflow that can look up the last shoe order & place the same pair of shoes in their online shopping cart.

Recommendations — Recommendations are key when we have a large set of items that we’d like to recommend to users. Many ecommerce websites apply recommendation strategies to products; they can detect that people who bought a specific pair of shoes also often order a certain pair of socks. When a user puts those shoes in their cart, AI automatically recommends the same socks.

Role of workflow and rules in using AI predictions

Workflow and rules aren’t technically part of AI, but they’re an essential part of how AI is used. Take the following example. Let’s say that AI predicts a given customer has a 25% likelihood of not renewing their contract. Just knowing this is not enough — we need to do something about it. That’s where workflow and rules come into play. In this example, our workflow might mean kicking off a retention campaign when the AI predicts that a customer is unlikely to renew.

2. Take the First Steps in Using Artificial Intelligence for the Business

The first step in using AI effectively is to figure out just how to tell it what we really want to achieve. We do this by clearly defining, in measurable terms, what we are trying to predict.

The second step in using AI effectively is getting our historical data in order. As the saying goes, “The best predictor of future behavior is past behavior” and this also holds true for artificial intelligence.

The last step is to turn prediction into action. To make the most out of AI we must have a concrete definition of what outcomes we want to optimize, historic data to train on, and a plan of action for how to use predictions.

3. Use Artificial Intelligence to Meet Our Business Needs

Different parts of a business can use AI to improve their business outcomes.

a) Marketing — Marketing is a great place for AI because companies usually have lots of data that can be used to target communications and send relevant messages.

If you’re marketing through email, there are a few questions that can have a huge impact on your campaigns. Will your customers open the email? Will they click through it? Will they act on it? Will they unsubscribe? These are yes or no questions that AI can use to make predictions about future recipients. This means you can send emails to prospects who are likely to open them without unsubscribing. It also means you can know the right channel to use for every customer, such as using push notifications instead of emails.

AI can also help send messages at the right time using Send Time Optimization. Send Time Optimization helps predicts the best time to send a communication for the highest response rate, specific to each person. You also want to send the right number of messages so you don’t accidentally annoy the customer to the point that they unsubscribe. With tools like Einstein Engagement Frequency, AI predicts the right number of communications to send without going overboard.

AI also uncovers why questions are answered the way they are. Market insights that might be overlooked by us humans are identified by AI and can be used to craft better communications that resonate with your customers.

b) Sales Productivity — AI can elevate your sales game by using historical sales data to predict the best possible sales opportunities. Imagine an inside sales rep who has a list of leads, organized by how likely they’ll convert. That rep is going to spend his time connecting with customers at the top of the list and avoiding cold leads.

c) Customer Service — AI could help by reading through emails, doing the case classification based on past inquiries, and then automatically routing the emails to the right person. Cases will get into the hands of the right agent faster Or AI could scan those notes in real time and recommend relevant articles that are known to solve similar problems. This new agent provides highly informed support even on their first day on the job.
Finally, instead of tying up an agent, customers can start a conversation with a chatbot.

d) Retail and Commerce — When shoppers browse online stores, they want an experience that caters directly to them. AI can meet this expectation by producing personalized recommendations for your customers. Historic data tells AI which products are frequently bought together. So if a customer chooses a product, your site can automatically show an offer for a discounted bundle, right on the product page.

Salesforce Einstein Basics

Einstein is Your Smart CRM Assistant, and it can be viewed as two categories.

  1. Einstein Out-of-the-Box Applications
  2. Einstein Platform

Einstein Out-of-the-Box Applications

Einstein infuses AI into all of the Salesforce apps (Sales Cloud, Service Cloud, and so on) — a built-in smart assistant — so that every business user in every role, function, and industry can be assisted right inside of the Salesforce product that they use every day.

Einstein Platform

The Einstein Platform includes powerful tools that allow admins and developers to build a customized smart assistant for their business. You can build an assistant that uses voice input, natural language understanding, voice output, intelligent interpretation, and agency components to better help your business interact with and understand its customers. You can also build capabilities that allow your customers to interact with smart assistants, giving quick answers to questions they have, and solving routine cases for them.

With as little friction as possible, Einstein allows all Salesforce users to:

  • Discover insights that bring new clarity about your company’s customers.
  • Predict outcomes so your users can make decisions with confidence.
  • Recommend the best actions to make the most out of every engagement.
  • Automate routine tasks so your users can focus on customer success.

Einstein can Specifically Benefit My Business

In IT, Einstein helps build intelligent apps, business processes, and workflows for every function and industry.
In Sales, Einstein helps guide reps to the best leads and opportunities so they increase conversion rates, and close more deals.
In Service, Einstein helps customers find answers instantly on their channels of choice and helps agents resolve cases faster by triaging cases and recommending the right articles.
In Marketing, Einstein helps marketers send the right content, to the right customer, at the right time, on the right channel, thus increasing customer engagement.
And for Commerce, Einstein helps retailers recommend the best product to each customer, at the right time, boosting revenue.

Einstein Out-Of-The-Box Applications

1. Sales Cloud Einstein — For Sales rep.

  • Boost win rates by prioritizing leads and opportunities most likely to convert.
  • Discover pipeline trends and take action by analyzing sales cycles with prepackaged best practices.
  • Maximize time spent selling by automating data capture.

2. Service Cloud Einstein — For Service agents.

  • Accelerate case resolution by automatically predicting and populating fields on incoming cases to save time and reduce repetitive tasks.
  • Increase call deflection by resolving routine customer requests on real-time digital channels like web and mobile chat or mobile messaging.
  • Reduce handle time by collecting and qualifying customer info for seamless agent handoff.
  • Solve issues faster by giving your agents intelligent, in-context conversation suggestions and knowledge recommendations.

3. Marketing Cloud Einstein — for marketing team

  • Know your audience more deeply by uncovering consumer insights and making predictions.
  • Engage more effectively by suggesting when and on which channels to reach out to customers.
  • Create personalized 1:1 messages and content based on consumer preferences and intent.
  • Be more productive by streamlining marketing operations.

4. Commerce Cloud Einstein

  • Increase revenue by showing shoppers the best products for them, and eliminate the time-consuming activity of manually merchandising each individual page.
  • Create highly visual dashboards to get a snapshot of your customer’s buying patterns and use these dashboards to power up your merchandising.
  • Personalize the explicit search (search via the search box), implicit search (browsing in the storefront catalog), and category pages for every shopper, saving your customers time and bringing your business more revenue.

Einstein Platform Products

  1. Einstein Bots — Einstein Bots allow you to build a smart assistant into your “customers” favorite channels like chat, messaging or voice. Einstein Bots use Natural Language Processing (NLP) to provide instant help for customers by answering common questions or gathering the right information to handoff the conversation seamlessly to the right agent for more complex questions or cases.

2. Einstein Voice — Einstein Voice enables all users to talk to Salesforce from any device. Einstein Voice is broken down into two buckets: enabling your organization (Einstein Voice Assistant), and enabling your customers (Einstein Voice Bots), with a smart assistant they can talk to.

a) Einstein Voice Assistant — Using Einstein Voice Assistant, you can enable anyone in your organization to talk to Salesforce.

b) Einstein Voice Bots — With Einstein Voice Bots, your customers can interact with your brand with their voice.

3. Einstein Prediction Builder — Einstein Prediction Builder is a simple point-click wizard that allows you to make custom predictions on your non-encrypted Salesforce data, fast. You can create predictions for any part of your business — across sales, service, marketing, commerce, IT, finance, and even HR — with clicks, not code.

4. Einstein Next Best Action — Einstein Next Best Action (NBA) allows you to use rules-based and predictive models to provide anyone in your business with intelligent, contextual recommendations and offers. Actions are delivered at the moment of maximum impact — surfacing insights directly within Salesforce.

5. Einstein Discovery — Like Einstein Prediction Builder, Einstein Discovery also predicts outcomes without requiring your own data scientist.

6. Einstein Vision and Language — Einstein Vision and Language are a set of APIs and services for Salesforce developers to use to add deep-learning capabilities to any application, ultimately allowing end users to classify images and extract meaning from text.

Einstein Vision consists of Einstein Object Detection and Einstein Image Classification. Together, these APIs harness and make sense out of unstructured data from images to help employees classify them at scale.

Reps at your business can take photos of the equipment, and with the help of Einstein Image Classification, they’d be able to understand whether the piece of equipment is damaged, where the damages are, and be given an estimate on how much it will cost to repair. This will take the guesswork out of inspecting all pieces of equipment, and it will save your reps a ton of time.

Einstein Object Detection extracts and contextualizes objects in images.

Einstein Language consists of Einstein Sentiment and Einstein Intent. Together, these APIs harness and make sense out of unstructured data from text to help better understand your customers.

Using positive and negative sentiment filters from Einstein Sentiment, your marketers understand who likes or dislikes the sweatshirts, and why they do, so that they can adjust their marketing tactics accordingly. Using Einstein Intent to categorize different text, your marketers can categorize what customers are saying about the product, whether they’re talking about the color, texture, durability, and more. This knowledge inherently your team become better marketers and better sellers.

Responsible Creation of Artificial Intelligence

  • To remove bias from our data and algorithms to create ethical AI systems at our company.

Bias — In the context of statistics, bias is systematic deviation from the truth or error.

Fairness — It is defined as a decision made free of self-interest, prejudice, or favoritism. In reality, it’s nearly impossible for a decision to be perfectly fair.

Create an Ethical Culture

  1. Build Diverse Teams.
  2. Translate values into processes. — This can be put into practice by Incentive structures, Resources and Documentation and Communication.
  3. Understand your customers.

Basics of Artificial Intelligence

Artificial intelligence — It is an umbrella term that refers to efforts to teach computers to perform complex tasks and behave in ways that give the appearance of human agency. Often they do this work by taking cues from the environment they’re embedded in. AI includes everything from robots who play chess to chatbots that can respond to customer support questions to self-driving cars that can intelligently navigate real-world traffic.

Machine Learning (ML) — A specific technique that allows a computer to “learn” from examples without having been explicitly programmed with step-by-step instructions. Currently, machine learning algorithms are geared toward answering a single type of question well. For that reason, machine learning algorithms are at the forefront of efforts to diagnose diseases, predict stock market trends, and recommend music.

Types of bias that can enter an AI system

  1. Measurement or Dataset Bias
    When data are incorrectly labeled or categorized or oversimplified, it results in measurement bias. Measurement bias can be introduced when a person makes a mistake labeling data, or through machine error. A characteristic, factor, or group can be over- or underrepresented in your dataset.

2. Type 1 vs. Type 2 Error
Think of a bank using AI to predict whether an applicant will repay a loan. If the system predicts that the applicant will be able to repay the loan but they don’t, it’s a false positive, or type 1 error. If the system predicts the applicant won’t be able to repay the loan but they do, that’s a false negative, or type 2 error. Banks want to grant loans to people they are confident can repay them. To minimize risk, their model is inclined toward type 2 errors. Even so, false negatives harm applicants the system incorrectly judges as unable to repay.

3. Association Bias
When data are labeled according to stereotypes, it results in association bias.

4. Confirmation Bias
Confirmation bias labels data based on preconceived ideas.

5. Automation Bias
Automation bias imposes a system’s values on others.

6. Societal Bias
Societal bias reproduces the results of past prejudice toward historically marginalized groups.

7. Survival or Survivorship Bias
Sometimes, an algorithm focuses on the results of those were selected, or who survived a certain process, at the expense of those who were excluded.

8. Interaction Bias
Humans create interaction bias when they interact with or intentionally try to influence AI systems and create biased results.

Entry points for bias to enter an AI system

  1. Assumptions
  2. Training Data
  3. Model
  4. Human Intervention (or Lack Thereof)

Remove Bias from Your Data and Algorithms

Manage Risks of Bias

  1. Conduct Premortems
  2. Identify Excluded or Overrepresented Factors in Your Dataset

Below are a couple ways that we can address bias in our data.

What: Statistical patterns that apply to the majority may be invalid within a minority group.

How: Consider creating different algorithms for different groups rather than one size fits all.

What: People are excluded from your dataset, and that exclusion has an impact on your users. Context and culture matter, but it may be impossible to see the effects in the data.
How: Look for what researchers call unknown unknowns, errors that happen when a model is highly confident about a prediction that is actually wrong. Unknown unknowns are in contrast to known unknowns, incorrect predictions that the model makes with low confidence.

3. Regularly Evaluate Your Training Data

Happy Learning! ✍️

Please follow me at Twitter : https://www.twitter.com/sunilbhardwaj1

LinkedIn : https://www.linkedin.com/in/sunilbhardwaj10

References:

Sunil Bhardwaj
Sunil Bhardwaj

Written by Sunil Bhardwaj

I'm Salesforce CRM Analytics Ambassador (2023 & 2022). I'm working with HCL as Salesforce Lead Consultant. I always enjoy helping people & being a Trailblazer!

No responses yet