Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Our Sales Team Scores Leads by Instinct and Good Ones Go Cold. How Do We Fix It?
Problems We Solve

Our Sales Team Scores Leads by Instinct and Good Ones Go Cold. How Do We Fix It?

When reps pick leads by instinct, strong ones sit untouched. We build machine learning lead scoring from your CRM history so the best leads get called first.

Updated 3 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

When salespeople choose which leads to call by instinct, they favour the ones that look familiar and leave others untouched until they go cold. A lead scoring model trained on which past leads actually became customers in your CRM ranks every new lead by likelihood to buy, with the reasons shown, so follow-up order is based on evidence rather than on who grabbed the lead first.

The lead nobody called

A lead comes in on a Tuesday afternoon: a company you have not heard of, a vague enquiry, a job title that does not scream decision maker. It sits in the CRM. The reps are busy with leads that look more promising, the ones from big names or with detailed messages. By Friday someone gets round to it. The prospect has already signed with a competitor who called back within the hour.

Meanwhile the leads that looked good on paper often go nowhere. The big-name company was a student doing research. The detailed enquiry was a supplier trying to sell to you. Everyone in the team has their own sense of what a good lead looks like, and nobody has checked it against what actually closed.

Why instinct gets it wrong

Salespeople remember their big wins and the patterns that led to them. That memory is real but narrow. It overweights the memorable deals and misses the quiet signals that predict buying in your particular market, such as which page someone viewed, how they found you, the size of their company, or the time between visits.

Points-based scoring in HubSpot or Salesforce was meant to fix this, but the points are usually set by someone's opinion too: ten points for a demo request, five for a download. Nobody goes back to check whether the points match reality, so the score gets ignored and cherry-picking carries on.

What instinct-led follow-up costs

PatternWhat it costs
Unfamiliar leads left waitingGood prospects go cold or go to a faster competitor
Time on attractive dead endsReps chase leads that were never going to buy
Points scores nobody trustsThe CRM holds a number that does not change behaviour
Uneven lead sharingSenior reps take the best-looking leads and juniors get the rest
Marketing blind spotsNo clear view of which channels bring buyers rather than clicks

Response time matters in most markets, and the lead you get to last is often the one you lose. Getting the order of follow-up right is cheap compared with generating more leads.

How we build lead scoring from your own outcomes

  1. We export lead and opportunity history from your CRM, such as HubSpot, Salesforce, Pipedrive or Zoho, including which leads became customers and which did not.
  2. We join it with behaviour data where you have it: website visits from your analytics, form answers, email engagement, the source and campaign that brought the lead in.
  3. We train a model on past outcomes so it learns what actually predicted a sale in your business, and test it on recent leads it has not seen.
  4. We write the score back into the CRM as a field, with the top reasons in plain words, for example "visited pricing page twice" or "company size matches past customers".
  5. We set up a view or routing rule so the highest-scoring new leads reach a rep first, and low-scoring ones go to a nurture sequence rather than being ignored.
  6. We compare scores with results each month and retrain when your market, products or campaigns change.

We also look at the reps' own judgement. Where it consistently beats the model on certain types of lead, that tells us something is missing from the data, and we try to capture it.

What changes for the sales team

The CRM view each morning shows new leads in order of how likely they are to buy, with the reasons. Reps call the strong ones first, including the unfamiliar companies they would have skipped. Weaker leads are not thrown away; they are nurtured by email until they show more interest.

Sales managers get an honest picture of which sources bring buyers, which helps marketing spend where it counts.

It also ends a lot of friction inside the team. When leads are ranked by evidence rather than grabbed, the argument about who got the good ones goes away, and junior reps get a fair share of the leads that actually close.

Is this your situation?

  • Reps decide which leads to call first based on how they look.
  • Good leads have gone cold because nobody picked them up in time.
  • Your CRM has a lead score that nobody trusts or uses.
  • You have at least a year or two of leads with known outcomes in the CRM.
  • Marketing cannot say which channels produce customers rather than enquiries.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

How many past leads do we need?

Enough closed-won and closed-lost examples for patterns to show. If you only have a handful of wins, a simpler, rules-based score reviewed against outcomes may be the better start.

Our CRM data is messy. Does that stop this?

It limits it. Outcome fields that are rarely updated are the most common problem, and fixing how deals are closed out in the CRM is often part of the work.

Will the sales team accept it?

They are more likely to if they can see the reasons behind each score and if early results are shared openly. We involve them from the start.

What drives the cost?

The number of data sources beyond the CRM, the quality of outcome data, and how the score is used in routing.

What do you need from us?

CRM access or exports, analytics access if you want behaviour data included, and time with a sales manager.

Keep reading

More on Problems We Solve

Start here

Tell us which decision is running on instinct

Describe what you are trying to predict, what data you hold and who acts on it. We will tell you honestly whether machine learning fits, and if a simpler fix would do the job, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →