Real Estate Intelligence Series | Module 2 of 6

Lead scoring:
who really buys - and who is just looking?

Of 40 enquiries per property, 3 are serious buyers. Your team spends 80% of its time on the wrong 37. A machine-learning model identifies from search behaviour, contact patterns and financing signals whom you should open the door for first.

01 The problem - every viewing costs 2.5 hours

Travel, preparation, viewing, follow-up - and 85% lead to nothing

An average property generates 38 enquiries, leads to 12 viewings and ends in 1.4 offers. That means: 10 of 12 viewings are wasted time. For an office with 32 agents and 15 active properties each, that is 4,800 unnecessary viewings per year - or 12,000 working hours.

The solution is not fewer viewings - it is the right ones first. Whoever prioritises the serious buyers sells faster and wastes less time on "property tourists".

4,800 unnecessary viewings = €360,000 of lost working time

At 2.5h per viewing × €30 full cost/hour. This time is missing for acquisition and closings.

Enquiry data
Behavioural signals
Random forest
Lead score
Prioritisation

02 Data basis - 18,600 enquiries, 12 months

Every enquiry with 14 behavioural signals - from first contact to closing

▸ Output
Leads: 18,600 | Conversions: 2,976 | Rate: 16.0%
18,600
Enquiries / year
16.0%
Conversion rate
84%
Non-buyers
2,976
Real buyers

03 Signals - what separates buyers from tourists

5 behavioural patterns nobody tracks systematically

Conversion rate by financing status
↳ The strongest signal

Leads with confirmed financing have a 38% conversion rate - 6× higher than leads without any financing information. But: only 15% of enquiries contain this info. The model learns to compensate for the missing information from proxy signals: message length, follow-up-question frequency and response time correlate strongly with financing readiness.

Conversion rate by response time (minutes)
↳ The speed indicator

Leads who reply within 30 minutes buy with 28% probability. After 4 hours the rate drops to 9%. Response time is no accident - it measures urgency and emotional commitment. A lead who reacts immediately has already decided to search.

Conversion rate: follow-up questions × budget match

04 Model - random forest with probability output

Not yes/no, but a purchase probability from 0-100%

0.72
Precision
0.84
Recall
0.91
AUC-ROC
Top 20%
contains 68% of buyers
↳ The practical translation

Recall 84%: the model finds 84% of all real buyers. The top 20% of leads contain 68% of all closings. That means: if your team works the top-20% leads first, you reach two thirds of all buyers with a fifth of the effort. The remaining 80% of enquiries can be served with standardised replies and self-service.

Feature importance - what gives a buyer away

05 Lead dashboard - what it looks like day-to-day

Every enquiry automatically receives a score from 0-100

412
Hot leads (>70)
1,240
Warm leads (30-70)
2,148
Cold leads (<30)
3,800
Leads this month
L-04281 · Family · 3-room flat, Südvorstadt
Score: 87 / 100
Signals: financing confirmed · 3 follow-up questions in 2 days · response time 12 min · budget match 98% · owns a property (sale planned)
Recommendation: offer a viewing immediately. Priority 1.
L-04293 · Couple · house, southern suburbs
Score: 74 / 100
Signals: financing in progress · message of 120 words (detailed questions) · 5 listing views · weekend enquiry
Recommendation: viewing within 48h. Ask about financing status.
L-04310 · Single · penthouse, city centre
Score: 45 / 100
Signals: no financing information · 8 enquiries on different properties · short standard message · but: budget match 102%
Recommendation: qualification call. Could be an investor - or a tourist.
L-04322 · Unknown · flat, Westend
Score: 12 / 100
Signals: 14 enquiries in 3 months (never a viewing) · no financing hint · response time >24h · budget match 68%
Recommendation: auto-responder. Do not prioritise.

06 Business impact - winning time back

Fewer viewings, more closings, higher agent satisfaction

Additional revenue from lead prioritisation
€612,000
Additional revenue / year
-42%
Unnecessary viewings
CategoryAmount/yearMechanism
Time saved → more closings€340,0002,016 viewing hours saved → 40 additional deals
Faster reaction to hot leads€178,500Buyers served 48h earlier → 15% fewer drop-offs
Automation of cold leads€93,500Standard workflow instead of manual handling
↳ The hidden effect

The biggest lever is not the time saved itself - it is that hot leads get served faster. Currently a top lead waits just as long as a tourist, because the queue is FIFO. With scoring, the best buyer is contacted within 2 hours instead of after 2 days. That reduces drop-offs by 15% - at an average commission value of €8,500 per deal.

07 Next steps for your brokerage

From score to automatic prioritisation

① CRM integration

An automatic score for every new lead in the CRM. Colour coding: red/yellow/green. Sorting by score instead of arrival time.

② Auto workflows

Cold leads: automatic listing dispatch. Warm leads: qualification-call reminder. Hot leads: instant notification to the responsible agent.

③ Feedback loop

Every closing and every rejection flows back into the model. The score gets more accurate every month - a self-learning system.

What lead scoring could look like for you is shown in our data science consulting for agents.

All 6 modules: AI for real estate agents