Untitled presentation (1)

AI for Sales - Calculating the Sales Forecast

Authored by Ric Ratkowski on July 22, 2019


I mentioned in my first blog on AI for Sales, when you hear the phrase “AI for sales forecasting” it feels like the solution is an algorithm to predict “the sales number”.  This is only partially correct.  While the ultimate goal is an accurate sales forecast, AI for sales forecasting requires artificial intelligence to be infused throughout the entire sales process.   The last 6 blogs have walked through different AI use cases for each of the different areas supporting the sales process to build a foundation for applying AI to create a more accurate sales forecast. 

With that background we are ready to review AI use cases for calculating different versions of the sales forecast.

Different Versions of the Sales Forecast

Before we dig into AI for sales forecasting use cases, we need to level set on forecasting in general.

Forecasting is the process to predict or estimate a future event or trend.  The process uses multiple methods for estimating outcomes of future events to feel comfortable with a value.  As an example, the diagram below shows alternate methods for figuring in on a price to sell your home.



The difference between the method “AI says $425,000” is the other methods are m

anually performed. The two outer methods, Buyer Valuation and Seller Valuation could be more biased.  The inner three valuations focus on different specific methods of forecasting

g.  The AI forecast may be more complete because it uses more factors for the estimate and could potentially include factors from all three methods.  The importance of the AI forecast is not as much about the number it is forecasting but more about understanding what drives that number.  If you understand what drives the outcome you can focus on those tasks to drive it higher.  As I’ve mentioned in previous blogs, it is important AI is applied as a “glass box” and not a “black box”.

Current State of Sales forecasting.

Most companies have a forecast method best described as “everybody does their own thing”, within some general frameworks of sales forecasting.  It is a fragile labor-intensive process, managed by one person and completed in a way they feel most comfortable, it requires a number of different technologies like CRM application, data extracts, and Excel.

The general frameworks they create their forecast with fits into one or all of the following frameworks:

  • Weighted Pipeline – Apply a closing probability to “live” opportunities by pipeline stage. The sales forecast for a given quarter equals the amount of the opportunities closing in the quarter multiplied by their closing probability by stage.
  • Forecast Categories – In this framework the sales rep identifies the sales opportunities they will “commit” to closing this sales period and which other sales opportunities could also close if this quarter hits “best case”.
  • Time Series Forecasting – this method forecasts future events based on known past events. It assumes there is a cyclical pattern to sales.  Time series generally assumes patterns of spending and number of sales reps added will be consistent with past trends.  Time Series Forecasting of sales for Business-to-Business companies has limited applicability because it ignores things like changes in marketing spending, changes in company focus or partnerships, accelerated market growth and adding sales reps.  An enhanced method of time series – “autoregressive Integrated Moving Average” allows for the inclusion of other outside independent variables. 

These methods are significant because as we apply Artificial Intelligence, we use these forecasting frameworks.  The difference is AI will be providing the observations, opportunity selection and percentages based on past sales patterns in a systematic, unbiased manner to create a sales pipeline driven forecast.

Three Use Cases for Numerically Calculating the Sales Forecast

The following three use cases help define additional automated forecast methods for a pipeline-based sales forecast.  The table below identifies key challenges creating a sales forecast and maps them to use cases where AI can be applied to help.


Use Case

  • Understanding the impact of opportunities not yet created at the beginning of the sales cycle that will close by the end of the sales cycle.
  • Apply AI to understand opportunities generated and closed in the same sales period based on past sales patterns.
  • Understanding sales rep biases vs actual track record for predicting what they are going to close in the period on a sales category/rep commit type forecast.


  • Use AI to assist in the generation of the sales rep forecast (category forecast) by providing benchmarks and patterns from past sales periods that suggest:  the percent to use to mark up or down the sales rep forecast based on historic sales rep biases; when an opportunity fits the profile of a “rep commit” but hasn’t been categorized by the sales rep that way.
  • Understanding how time degrades the weighted sale pipeline forecast.
  • Provide an AI based weighted [stage based] based on past sales and time patterns.


The following provide more information on each of the three use cases.

The first use case helps to understanding the impact of opportunities not yet created at the beginning of the sales cycle that will close by the end of the sales cycle.  It does this by using the past history of close won and close lost opportunities that were created during the same sales period they closed in.  It models the expected sales using “Autoregressive Time Series”.  Autoregressive time series recognizes there are:

  • External activities such as marketing campaigns, events, number of sales reps, etc. that represent additional variables that can drive sales
  • A cyclical pattern to sales made up of a multi period trend, sales cycle in a sales period and random noise in the process.

The results of these calculations can be interpreted and managed via the following two graphs.

AI for Sales Current Cohort to Close   AI for Sales Current Opportunity Development
The above graph shows the expected sales to be generated in this sales period attributable to leads generated in this sales period and how it decreases over time.    The graph on the left is dependent on creating a targeted number of leads in the quarter.  The above graph shows the targeted leads to be created (dash line) and the actual leads created (solid line). 


The forecast from future sales leads is added to the AI based sales pipeline forecast to arrive at the total forecast for the sales period.

The second use case is to apply AI rigor to assist in the generation of a category-based forecast.  It is AI assisted because AI is making two recommendations with regard “Rep Commit” and “Best Case”.   As was mentioned above in the “Current State of Sales Forecasting” section, the Forecast Categories method is where you ask the sales rep to identify their sales opportunities they will “commit” to closing this sales period and which other sales opportunities could also close if this quarter hits “best case”.   

AI is used to make two recommendations with regard “Rep Commit” and “Best Case”:

  • The first recommendation is highlighted in yellow under the “AI Schedule to win Rate” column in the diagram below. This is the AI derived “recommendation” based on past history of the overall accuracy of the rep commit and best-case estimates from the sales rep.
  • The second recommendation is the row Commit Suggestions. This is the AI calculation suggesting that some opportunities categorized as Engaged or Stalled should be moved up to the Rep Commit stage.

The table below identifies a sample “forecast category” spreadsheet.  The column highlighted in green allows the person doing the forecast to discount the rep commit based on their feel for the opportunities and where the forecast will end up.  They fill in this column by referring to the AI Scheduled to win rate column and personal experience. 

AI for Sales Forecast Category Example

The third use case provides a weighted [stage] based sales forecast.  The stage-based AI calculated forecast assigned a close rate percentage to the opportunities in the sales pipeline, taking into consideration:

  • The historic sales patterns of opportunities in each stage.
  • The time-based sales cycle patterns within the sales period.
  • Clustering of sales opportunity by dollar value and AI close metrics.

The close metrics are generated by AI to focus on the most significant attributes of the opportunity that impact Close-Won opportunities. 

Clustering based on the dollar value of opportunities is required because we either close opportunities or we don’t.  An average doesn’t work.  If there are two opportunities, one for a dollar and one for one million dollars and we are projected to close one opportunity.  We will either have one dollar of sales for the period or one million dollars for the period.  AI uses clustering to group sales opportunity by both stage and value to identify the range of deals that will close.


This blog covered three use cases for applying AI for calculating the numeric sales forecast.  Beyond the use cases of defining the forecast, two key requirements of applying AI for Sales are:

Understanding what drives the outcome (forecast/opportunity status/ account email domain, etc.) is more important than the actual forecast itself”.  Understanding what drives the forecast allow you to make changes to increase the forecast.   

Artificial intelligence needs to be infused throughout the entire sales process.  Good forecast algorithms on bad data just renders a bad forecast.  AI needs to be infused into data collection, marketing, pipeline management, coaching and the sales forecast calculations.  

Seventh In a Blog Series on “AI for Sales”

This is the seventh blog in the series - AI for Sales Forecasting. 

The first blog: Artificial Intelligence [AI] For Sales Forecasting provides an overview of AI for Sales and outlines of what will be covered in this blog series.

The second blog:  AI for Sales – AI/Machine Learning Primer for Sales provides a baseline understanding of AI and examples of how it is applied.

The third blog:  AI for Sales - In the Marketing Funnel

The fourth blog:  AI for Sales - Enhanced Data Collection

The fifth blog:  AI for Sales – AI for Sales – Guided Selling

The sixth blog:  AI for Sales – Sales Pipeline Management and Sales Rep Coaching

Then next blog will be this last blog in the series "AI for Sales".  It will summarize the key use cases for AI for Sales across data collection, marketing, pipeline management, coaching and calculating the sales forecast.

Subscribe to our newsletter!

Leverage these best practices with automation and AI driven by TopOPPS

Learn how our customers are winning with artificial intelligence in their CRM:

  • Predictive Sales Forecasting
  • Automated Pipeline Management
  • Significantly More Updates from Reps

Watch Videos

More Recent Posts:

March 23, 2020

Tactical Best Practices for B2B Sales-Company Attributes

This blog reviews the tactical best practices for collecting information about accounts [companies] where you have sales opportunities or are targeting for a sales opportunity.     This blog is the fifth blog in the series “Best Practices for B2B Sales”.  The first blog organized the best practices along five key areas. The second blog divided up the first area, data access, into four key areas.  This blog focuses on the last area of data access and collection. ...

Artificial Intelligence, AI for Sales, best practices

March 9, 2020

Best Practices for B2B Sales-Opportunity Attributes & Buyer Team Tracking

This blog reviews the tactical best practices for collecting information about a sales opportunity [opportunity attributes] and information about buying team members and roles.  Much of the information about the sales opportunity is not available electronically. The objective is to make it as easy as possible for the sales rep to enter it and provide benefit to the sales rep by presenting it in an intuitive manner to keep both sales reps and sales management up to date on the opportunity. ...

Artificial Intelligence, AI for Sales, best practices

February 25, 2020

Tactical Best Practices for B2B Sales - Data Access-Sales Interactions

The typical situation we found many of our sales prospects in when they were considering our solution is: Sales reps don’t timely update their sales force automation platform Sales reps don’t have sufficient, timely and accurate information about their sales opportunities Sales Managers don’t have the data they needed to accurately forecast sales for the quarter or coach their direct reports on specific opportunities The end-of-quarter is a mad scramble and there is no visibility into the deals to focus on Forecast accuracy suffered ...

CRM, Sales Tools, AI for Sales, sales best practices

February 11, 2020

Introduction to Best Practices for B2B Sales - Data Access

With all the advances in sales technology and analytics, you would expect sales teams to have all the data they need about each sales opportunity to accurately forecast sales.  However, that isn’t the case.  Research by Bohanec, Kljajic Borstnar and Robnik-Sikonja in the study “Integration of machine learning insights into organizational learning, A case of B2B sales forecasting” found that: ...

Sales Rep, Artificial Intelligence, AI for Sales, best practices

January 21, 2020

Best Practices for B2B Sales Pipeline and Forecast Management

New year, new blog series!   The new blog series will focus on “Best Practices for B2B Sales Pipeline and Forecast Management”.   This covers a big area so this series could take most of 2020 to complete and its frequency will be more often than once a month.    The reason for this blog series is companies continue to rely on human intuition and instinct to produce sales forecasts.  They continue to spend significant time managing, manually reviewing and updating the sales forecast despite advances in sales technology. ...

Sales Pipeline Management, AI for Sales, Guided Selling, best practices

January 21, 2020

Brainshark and TopOPPS Form Partnership to Combine Sales Readiness with AI-Driven Sales Pipeline and Forecast Management

The Integrated Solutions Will Provide Deep Insights into Pipeline Activity and Forecasting - Enabling Targeted Learning that Elevates Sales Performance WALTHAM, Mass. and ST. LOUIS, Jan. 21, 2020 /PRNewswire/ -- Brainshark, Inc., the industry's only data-driven sales readiness platform, and TopOPPS, a leading provider of artificial intelligence (AI)-based sales pipeline management and forecast predictability solutions, today announced they have formed a strategic partnership. The partnership – which includes an integration of Brainshark and TopOPPS solutions – will empower sales organizations to deliver "in-the-moment" guidance that improves reps' skills at key points throughout the sales cycle. ...

AI for Sales, Sales Enablement, Guided Selling

December 13, 2019

Sales Superpowers Need 'In-Context' for Sales Engagement

  SiriusDecisions outlines “One Solution for Sales Superpowers”.  [Spoiler alert] - it is sales engagement.   If it is “the one solution” to supercharge your revenue engine, why isn’t it widely used?   Why isn’t it the most popular application in the “sales world”?  We will get back to that, but first lets make sure we are on the same page. Sales Engagement Defined  Sales engagement is defined as interactions that take place between the buyer and seller.  Sales engagement includes four core functions based on SiriusDecisions definition:  calling/dialing, email, calendarizing and reporting. ...

Sales Operations, Sales Tools, Sales Pipeline Management, Strategic Partnerships

November 25, 2019

Strengthening the CFO-CRO Relationship Through the Sales Forecast

  The sales forecast is the linchpin of a company’s future.  If it is right and can be trusted the companies’ operations run smoother and its financial stability is more secure.  Typically this isn't easy.  The sales forecasting process is shared by the Chief Revenue Officer[CRO] and the Chief Financial Officer[CFO].  The challenge is both have different motivations on its accuracy and neither have a complete vision of its drivers or its accuracy.   When the forecasting process is trusted and transparent it relieves stress on both the CRO and the CFO.  This blog reviews how this can be accomplished.  ...

Sales Operations, Sales Tools, Sales Pipeline Management, Strategic Partnerships