Model Normalizations – Using your predictive model to score different segments of your business

Infer’s predictive models score and stack-rank prospective buyers on a 0-100 point scale based on their fit for a specific company’s product. For example, here is a typical distribution across an entire business:

All Prospects

Sometimes a model will score a certain subset of leads (e.g. leads from a specific geography, industry, product, etc.) lower than average because a company hasn’t historically focused on those types of leads. For example, prospects in EMEA might just score lower because you may have started selling to EMEA customers only recently. This can cause problems if left as-is because your sales reps (or marketers) who focus on EMEA would only see Infer C and D-Leads, giving them limited insight with which to prioritize those leads. 

Two approaches to scoring leads – Fit vs. Behavior

This post originally appeared on the Salesforce Blog

While some companies aggressively pursue every lead that is created, others are leveraging lead scoring to work smarter. If you can programmatically spot your good leads, chances are you’ll be able to increase win rates and conversion.

So what makes a good lead?

A good lead has two key ingredients

Fit Score (also referred to as an explicit score)

Intended to capture how much an incoming prospect resembles a likely buyer. For example you might look at the lead’s company size, geographic location, industry, and job title, to determine if it is a fit. A quick look at its employer’s website might give you other clues regarding their business model or online presence.

Behavioral Score (also referred to as an implicit score)

Intended to capture how much a prospect is engaged with your company. This could include the lead’s website visits, form completes, email clicks, and maybe even application usage data.

Examples of External Signals Infer Tracks

Sales and marketing folks have been talking about lead scoring for years, so we often get asked “what’s different” about Infer’s way of doing things. One of the reasons Infer’s models perform so much better than traditional lead scoring is that our system pulls in several thousands of external signals, going well beyond what most organizations track in Salesforce.com or other CRM and marketing automation tools.

Signals

Broadly speaking, Infer gets these signals from three sources: crawling the web, purchasing data, and inferring signals from raw data sources. The last of these is the most subtle, and it’s our equivalent of Google’s secret sauce for web search.

Using Predictive Scoring to Bucket and Align Your Sales SLAs

A Sales SLA (Service Level Agreement) ensures that all of the leads marketing generates are followed up on by sales in a timely fashion. Most companies will create a tiered SLA based upon lead type — i.e. Contact Me Requests and Free Trials are top priority, while Webinar attendees and eBook downloaders may only warrant a single phone call.

Tarditional SLA

Does Predictive Scoring Work if You’re Trying to Enter a New Market?

Cracking New MarketsThis is a question that often comes up in conversations with our prospects and customers. What happens when you want to push into a new market where you haven’t had a track record of success? Does predictive scoring offer any value? Or does it become a self-fulfilling prophecy that limits your potential?

The short answer is yes. Predictive Scoring can be extremely helpful in breaking into new markets. Here are some things to think about…

Does Infer’s Predictive Scoring Look at the Person or the Company They Work For?

The short answer is both. Most of Infer’s customers are selling B2B products, so the first order of business is to make sure that the companies they target are good fits for their offering, and then look at who the individual buyers are. Even if a lead comes in with a CEO or VP title, the chances of converting that lead to a customer may be very low if their company is not a good fit for your product. 

Does Predictive Scoring Work if I’ve Got Bad Data?

People often ask us: “If I don’t have confidence in my data quality, how could predictive scoring possibly work?” Many businesses delay lead scoring initiatives while they wade through cumbersome data clean-up projects – leaving major revenue-driving opportunities on the table in the meantime.

But at Infer, our platform was designed to handle bad data, so we could ensure quick implementations and provide immediate value.