Related

Re-Blog: Why Visualizing Data is Important

on February 24

10 Questions to Ask Before Buying Sales Leads

on April 7, 2014

At the beginning of the project, we set out to show how the 2017 NCAA College Basketball Tournament could be a proving ground for Machine Learning analysis. There are very few places in the world where we can use the same model to predict multiple outcomes in a short period of time, have a ready-made scorecard (Vegas), have the general public understand what we are trying to do, and have a chance to “beat” the algorithm with their own knowledge.

You could say our findings have been a “Slam Dunk” (I couldn’t help myself).

Before diving into the results, I wanted the reader to understand what we were up against. It’s easy to pick chalk (always picking the better seed). In fact, that is how the games are supposed to work. The 8 seed is supposed to beat the 9. And for the most part, the NCAA does a decent job. Historically, only 26% of tournament’s games end in an upset (this includes games from all rounds). That’s 17 out of 64 games. This was never going to be easy.

 

Project Recap

We predicted 20 upsets and got 10 right (50%). We only missed predicting 3 upsets.

Using Vegas as a scorecard and having bet $100 “dollars” on each predicted upset, we would have ended up +$2,605 off our simulated bets (a 30% ROI)–the majority of this coming from long shot underdogs.

Think about this. If we would have bet all chalk on games except the ones the algorithm predicted as upsets, then out of 61 games we would have only missed 13. That’s 79% accurate!

Let’s look at this another way. Our algorithm predicted 77% (10/13) of something that is only 26% likely to happen in the first place. Now think about what you would do if you could identify an unlikely event in your business with 77% accuracy.

  • What would you do if you knew 77% of the customers who were going to leave before they left?
  • What would you do if you knew 77% of failed batches before they happened?
  • What would you do if you knew 77% of your plant’s machine failures before they happened?

Business Scenario

You have a theory that some of your clients would buy more “product” if they were called and offered an upgraded deal. However you don’t want to call all of your clients because you have so many. What you do have is a dataset of past customers that successfully responded to this type of nudge. Using your data, our machine learning algorithm could predict a set of your clients that would be 77% likely to purchase more product if called.

 

Game changer right?

 

Why this is huge

Our Machine Learning lower seed winning project was looking to predict as accurately as we could a lower seeded team winning in the NCAA tournament. Our stated goal from the beginning was to get 47% of our picks correct and a mere 10% ROI. We beat both of those goals. Our Machine Learning algorithm, which uses a custom optimization engine called Evolutionary Analysis, looked at a comparison of 207 different metrics of college basketball teams and their results in prior tournaments. It selected ranges of those 207 measures that best matched up with historic wins by lower seeded teams. We then confirmed that the range was predictive by testing the selected ranges against a “clean” historic data set. This comparison is how we got our goal percent and ROI. We then published our forecasts before each round was played – the results speak for themselves.

While we still have 3 games to go, our initial point that Machine Learning can help you be better at making decisions from your data has been proven. Implementing Machine Learning isn’t hard so long as your business has these three characteristics:

  • A data set with a large number of characteristics
  • A measure of success to optimize upon
  • A desire to learn from data to make changes in your organization

 

If this sounds like something that your business could use, please contact Nate Watson of CAN (Nate@CanWorkSmart.com) or Gordon Summers of Cabri Group (Gordon.Summers@CabriGroup.com) today.

 


Prediction Results

Here is a summary of our picks from the beginning of the project ($ indicates our successful pick where “money” was made):

East Tennessee St. over Florida
$ Xavier over Maryland
Vermont over Purdue
Florida Gulf Coast over Florida St.
Nevada over Iowa St.
$ Rhode Island over Creighton
$ Wichita St. over Dayton
$ USC over SMU
$ Wisconsin over Villanova
$ Xavier over Florida St.
Rhode Island over Oregon (tied with a minute to go)
Middle Tennessee over Butler
Wichita St. over Kentucky (tied with a minute to go)
Wisconsin over Florida (OT last second shot)
$ South Carolina over Baylor
$ Xavier over Arizona
Purdue over Kansas
Butler over North Carolina
$ South Carolina over Florida
$ Oregon over Kansas

And for those who are curious, our algorithm has detected one Final Four upset for this weekend:

Oregon over North Carolina

For more information about how we created the Machine Learning algorithm and how we kept score, please read our Machine Learning technical document. Additionally you can find results for the whole tournament here.


Related

Machine Learning Upset Prediction Project Proves its Value

on March 27

10 Questions to Ask Before Buying Sales Leads

on April 7, 2014
The Tableau data visualization above, found at Tableau Public, shows the “Top 100 Songs of All Time Lyrics”. Click here to hover over each square and see what words were used in which lyrics. Tableau is a software that converts data into graphs, charts, and images.

 

CAN’s data scientists love sorting through piles and piles of spreadsheets and numerical data, but it’s not for everyone. There are some amazing tools that convert raw data into visualizations. They help bring out the story of data, so everyone can understand it.

Here’s an old favorite from our blog about the importance of visualization. It’s a way for us at CAN to gear up for the next round of Tableau students at the Omaha Data Science Academy!

We are still accepting applicants for the third round of the Oma-DSA! You can apply here. We accept applications until three weeks before the start date, and start a waiting list after the spots are filled. 

 

Why Visualizing Data is Important


Related

Generating Sales Leads

on March 30, 2014
10 Questions to Ask Before Buying Sales Leads

Thinking about buying sales leads? Here are 10 questions that you should ask first.

1. What is the minimum purchase?

List brokers try to capture as much of your marketing budget as possible. They do this by setting minimum purchase amounts and charging for filtering: both encourage larger purchases. So while you might find a broker with low minimum purchases, there is a good chance they charge high fees to filter their lists.

The key is to find balance. Often, buying an extra thousand sales leads won’t cost as much as the first thousand. However, you might not want to use them all. You want to avoid using sales leads that don’t fit your target audience, because interrupting the wrong people is a good way to erode the credibility of your brand (and is a waste of your time and resources). Buying names and contact information is the cheapest part of marketing and selling. You should only use the leads that are the best fit for what you sell; even if that means not using every name.  Read more…


Related

Machine Learning Upset Prediction Project Proves its Value

on March 27

Re-Blog: Why Visualizing Data is Important

on February 24
Generating Sales Leads

Every sales organization requires three things: sales managers, salespeople, and sales leads. In principal, the formula is simple: the sales team will meet their quota if the sales manager focuses the salespeople on the right sales leads.

Most sales organizations know how to find salespeople and sales managers, leaving sales leads. There are 4 sources of sales leads: 1.) referrals, 2.) conferences and trade shows, 3.) inbound marketing and 4.) proactive sales. Each sources has its pros and cons: the key is selecting the right sources for what you sell.

For example, there are businesses where referrals are often the best or the only way to grow. These “word-of-mouth” businesses tend to offer services that are intimate, offer solutions to frequent problems, and have limited marketing resources.

However, most businesses need more than one sources of leads to maximize revenue. Not having the right combination of sources stagnates growth and increases your cost of client acquisitionDifferent lead sources vary in the amount of upfront investment, sophistication required, and payback period.

Read more…


What if you knew which prospects to focus on for the best results?

Working with a Top 10 Online University, CAN used predictive analytics and data science to find patterns in their admissions data to help them make better decisions and focus their efforts.

We developed a model showing which prospects were most likely to convert, which needed extra attention, and which were unlikely to enroll at all. Armed with these insights, they are able put their most valuable resources — time and money — towards building relationships with the prospects that mattered, instead of wasting their efforts trying to engage uninterested individuals. Read more…


What if you could determine — in advance — your most beneficial business relationships?

Our predictive models help you sort relationship opportunities to determine which are beneficial, and which are distractions. You will be able to focus your resources on the Requests for Proposals (RFPs) that will have the most impact on your organization.

To make business relationship decisions, companies and organizations often rely on solicited bids and RFPs. The problem is that responding takes time and money — often more than 20 hours for a basic RFP and weeks for a more complex RFP. This investment of resources makes it very important to select and respond to the RFPs you are most likely to win.

Using your existing data, and the knowledge and intuition of your team, we build a model that helps focus your efforts. You will be able to select the RFPs that you have the greatest chance of winning, allowing you to use your resources more effectively — and close more bids.  Read more…


What if you could increase loyalty — and revenue — by selling smarter to your existing customers?

By failing to recognize cross-, re-, and up-sell opportunities within your existing customer base, your organization can experience decreased share of wallet, decreased customer loyalty, and increased customer churn.

Using predictive analytics, we were able to increase the share of wallet and customer loyalty of a 12,000 member credit union.  We identified which members were most likely to need a home or auto loan — and which were most likely to leave. These insights allowed them to create a proactive sales approach targeting their most valuable existing customers. Read more…



Turn your accounting and customer data into sales — by focusing on the prospects and deals that are most likely to close.


Related

Get More Sales from Your Current Customers

on December 3, 2012

Net New Sales: Sell More by Selling Less

on December 17, 2012

There have always been two major ways to expand your business:  Grow it, or Buy it.  This brings up some interesting questions about which is more beneficial.  The correct answer is usually based on cost of customer acquisition and customer lifetime value.  Right now, with the cost of client acquisition being so high, companies are turning to buying distressed businesses.  One, it eliminates competition, and two, the customers can be acquired “on sale”.  While mergers and acquisitions are common across all industries, there seems to be a significant propensity for growth by buying in the banking industry.

The unique problem that is causing an increase in the ” buy them” thought process is that in banking their revenue generating power has dwindled with the decline of interest rates.   Not only that but as clients leave for competitors by natural attrition, there is a dire need for new customers.  Buying seems to solve both of these.

While it may solve the issue of new customers at a reduced cost, how to transfer the old customer base to the new bank has always been a major problem.  First, you have a bevy of new customers who have not gone through your buying process.  You have no idea who they are and why they are in the product they are in.  Secondly, you can fix problem number one by keeping the staff from the bought bank, but they’re not sure if the customers are in the correct products anymore either because they don’t know what products they have to sell. Read more…


Related

Machine Learning Upset Prediction Project Proves its Value

on March 27

Re-Blog: Why Visualizing Data is Important

on February 24

How many products can the average salesperson keep in their head while they are making reccomendations to customers? You will be shocked to find on average it is only 8.  What if 8 isn’t enough?  What if you have more than 8?  What if you have twice that?  Ten times that?

If you have more than 8 products, when a member of your sales team calls on a current client, they only recommend the products that they are most familiar with.  You have provided them an entire playbook, and they use only a tiny fraction.  Unless, those 8 products just happen to be the correct product for a customer, your sales staff just put a client into the wrong product.  They assumed that everyone was like them.

Think about that for a second.  The whole point of cross-sell is to keep your clients happy and purchasing from you. Matching the wrong product with the wrong person means reduced satisfaction, frustration, and loss of loyalty.  On the balance sheet, you are losing income, not maximizing profitability, and your salespeople are misusing their time.  How do you improve this? Read more…



Looking for something?