In anticipation of his upcoming conference presentation, Using Mileage Logs to Predict Successful Sales Behavior at Predictive Analytics World for Business New York, Oct 29-Nov 2, 2017, we asked Ron Cowan, Founder at Snowforce Data, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what behavior or outcome do your models predict?
A: Over the last 25 years in our work with CRM systems (now predominantly Salesforce®), much of the focus (and the data contents within these systems) has been around ‘user entered information’ such as notes about office visits, potential deals or opportunities in the pipeline, etc.
Elaborate dashboards and graphics are often provided analyzing inherently doubtful source data- a note entered manually by the user.
But ‘user entered’ data is inherently unreliable, inconsistent, biased and in many cases just not true. Did the sales rep really visit the prospect? How long did they stay at the office they noted a detailed visit about?
Expanding that line of thought leads sales management to wonder, “How many appointments do my reps really have?” and “How many appointments should they have each week?”
Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?
A: The recent introduction of smartphone based mileage capture tools (implemented for vehicle reimbursement) has provided an enormous side benefit, in that it has enabled the systematic and company-wide collection of true driver data to analyze.
Every vehicle stop and start (and corresponding address) is documented and fed to a central server.
In addition to understanding time spent driving we also learn the exact time spent at the specific address. In effect, we know the appointment could be 4 minutes or 90 minutes. This can provide significant insight when overlaid with the user entered note about the likelihood of a closed opportunity. We no longer have to rely on user entered notes in the CRM system.
But if only there was a way to bring the driver data into the CRM record? Well, we figured out a way!
Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: Most companies that have initiated smartphone based mileage capture have used the data to optimize their fleet and vehicle metrics; better trip planning and routing, enhanced territory coverage, etc. Sales planning and analysis is often not performed on this data and sales tactics and activity remains a tightly controlled mystery possessed by the sales manager (if they even really know where their reps are).
We overlaid smartphone based mileage capture on 25,000 medical office visits with the corresponding records inside Salesforce to gain an unprecedented insight into the true results of those visits.
Did the visit really happen? Did they visit lead to a sale? How many visits should a sales rep have per day, per month and how long should the visit on average be?
Q: What surprising discovery or insight have you unearthed in your data?
A: Several major insights were obtained from this data analysis.
The sheer amount of drive time of certain salespeople was shocking; one third of drivers spend more than 50% of their time behind the wheel.
We learned a metric regarding the actual number of appointments per week a sales rep should on average obtain in order to be successful (answer provided at our PAW NYC session!)
We identified a bias to visit certain favorite customers, while excluding visits to potentially more important prospects.
Can we predict the buying behavior of the client and the selling success of a specific rep based on thousands of trip starts and stops?
Yes we can!
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: Only 12% of organizations use any optimization to assist with salesperson appointment planning. It is left to managers in the field to direct the activity and 45% of reps use their instinct to prioritize face to face meetings.
Squeezing 0.5 more stops in a day translates into 120 more meetings per year for a salesperson. In larger organizations this type of analytic-based appointment planning can yield tremendous benefits.
Don’t miss Ron’s conference presentation, Using Mileage Logs to Predict Successful Sales Behavior on Tuesday, October 31, 2017 at 3:55 to 4:15 pm at Predictive Analytics World New York. Click here to register to attend. Use Code PATIMES for 15% off current prices (excludes workshops).
By: Eric Siegel, Founder, Predictive Analytics World
Eric Siegel is the founder of Predictive Analytics World (www.pawcon.com) — the leading cross-vendor conference series consisting of 10 annual events in New York, Chicago, San Francisco, Washington DC, London, and Berlin — and the author of the award-winning book, Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die – Revised and Updated Edition, (Wiley, 2016).