---
name: icp-account-modeling
slug: icp-account-modeling
description: This skill should be used when the user asks to "model ICP accounts", "build an ICP account model", "score account fit", "model accounts against ICP", "build an account scoring model", "rate accounts on ICP fit", "create an account fit model", "quantify account fit", "build a data-driven account model", or any variation of quantitatively scoring and modeling accounts against ICP criteria for B2B SaaS targeting.
category: general
---

# ICP Account Modeling

ICP account modeling scores every company in your pipeline, CRM, or target list on how closely it matches your ideal customer profile. The output is a numerical fit score per account that drives prioritization, routing, ABM tiering, and resource allocation. Instead of "this looks like a good account" (subjective), the model produces "this account scores 82/100 on ICP fit" (objective, comparable, actionable).

The principle: the model should predict which accounts are most likely to buy, retain, and expand. Build it from closed-won data, validate against churn data, and update quarterly. A model built from intuition rather than data will drift from reality within 6 months.

## The Account Scoring Model

### Scoring dimensions

| Dimension | Weight | What it measures | Data source |
|-----------|--------|-----------------|-------------|
| Company size | 20% | Employee count within ICP range | Enrichment (Apollo, Clearbit) |
| Industry | 20% | Vertical match to ICP verticals | Enrichment |
| Funding stage | 15% | Investment stage alignment | Crunchbase, enrichment |
| Geography | 10% | HQ in serviceable market | Enrichment |
| Tech stack | 15% | Uses tools you integrate with or compete with | Job postings, BuiltWith, enrichment |
| Growth trajectory | 10% | Headcount or revenue growth rate | LinkedIn, enrichment |
| GTM motion | 10% | Sales-led, PLG, or hybrid alignment | Inferred from team composition and hiring |

### Scoring rubric

For each dimension, score 0-3:

| Score | Meaning | Criteria example (company size, ICP = 50-500) |
|-------|---------|----------------------------------------------|
| 0 | No fit. Outside ICP entirely | < 10 or > 5,000 employees |
| 1 | Marginal fit. Edge of ICP | 10-49 or 501-1,000 employees |
| 2 | Good fit. Within ICP range | 50-200 or 201-500 employees |
| 3 | Ideal fit. Sweet spot | 100-300 employees (the range where you close fastest and churn least) |

### Calculating the weighted score

```
ICP Score = (size_score × 0.20) + (industry_score × 0.20) +
            (funding_score × 0.15) + (geo_score × 0.10) +
            (tech_score × 0.15) + (growth_score × 0.10) +
            (gtm_score × 0.10)

Normalize to 0-100 scale:
  Raw max = 3.0 (every dimension = 3)
  ICP Score (0-100) = (raw_score / 3.0) × 100
```

### Tier assignment

| ICP Score | Tier | Action |
|-----------|------|--------|
| 80-100 | Tier 1 (Ideal) | ABM 1-to-1 or 1-to-few. Highest priority outbound |
| 60-79 | Tier 2 (Good) | Standard outbound. May qualify for 1-to-few ABM |
| 40-59 | Tier 3 (Acceptable) | Lower priority outbound. Volume play |
| 20-39 | Tier 4 (Poor) | Nurture only. Don't spend sales time |
| 0-19 | Not ICP | Disqualify. Remove from outbound lists |

---

## Building the Model from Data

### Step 1: Define weights from closed-won analysis

Pull 50+ closed-won deals. For each dimension, calculate the win rate by score level.

**Example: Company size analysis**

| Size band | Won deals | Lost deals | Win rate | Score assignment |
|-----------|-----------|-----------|---------|-----------------|
| 1-20 | 2 | 18 | 10% | 0 |
| 21-50 | 5 | 15 | 25% | 1 |
| 51-200 | 22 | 8 | 73% | 3 |
| 201-500 | 15 | 7 | 68% | 2 |
| 501-1000 | 4 | 12 | 25% | 1 |
| 1000+ | 2 | 20 | 9% | 0 |

The dimension with the largest win-rate spread between best and worst segments gets the highest weight. If company size has a 63pp spread (73% - 10%) and geography has a 20pp spread, size is weighted higher.

### Step 2: Validate against churn data

Apply the scoring model to existing customers. High-scoring accounts should churn less.

| ICP tier (at time of purchase) | Churn rate (12 months) | NRR |
|-------------------------------|----------------------|-----|
| Tier 1 (80-100) | 4% | 125% |
| Tier 2 (60-79) | 10% | 108% |
| Tier 3 (40-59) | 22% | 95% |
| Tier 4 (< 40) | 40% | 75% |

If Tier 1 accounts don't churn significantly less than Tier 3, the model isn't predicting retention. Adjust weights.

### Step 3: Automate scoring in CRM

```
On account creation or enrichment update:
  → Query enrichment fields (size, industry, funding, geo, tech, growth)
  → Apply scoring rubric per dimension
  → Calculate weighted score (0-100)
  → Assign ICP tier
  → Store: icp_score, icp_tier, icp_last_scored
```

### Step 4: Quarterly calibration

- Re-run closed-won analysis with new data
- Check if Tier 1 still wins at 2x+ Tier 3 rate
- Check if Tier 1 still retains at 2x+ Tier 3 rate
- Adjust weights and score thresholds if needed

---

## Negative Scoring (Anti-ICP)

Some attributes should disqualify an account regardless of positive fit.

| Anti-ICP attribute | Penalty | Why |
|-------------------|---------|-----|
| Competitor company | -100 (instant disqualify) | Not a real prospect |
| Government / education (if not served) | -50 | Different buying process. Different requirements. Low close rate |
| Company < 5 employees | -40 | Too small to need your product. Can't afford it |
| No relevant department (e.g., no sales team for a sales tool) | -30 | No buyer for your product at this company |
| Sanctioned country | -100 (instant disqualify) | Can't sell |
| Known bad-fit vertical (from churn data) | -30 | Historical evidence of poor fit |

---

## Where the ICP Score Gets Used

| Function | How the score is used |
|----------|----------------------|
| List building | Filter for Tier 1-2 accounts only. Don't build lists of Tier 4 accounts |
| Lead routing | Tier 1 → senior AE or ABM. Tier 2 → SDR outbound. Tier 3 → automated nurture |
| Lead scoring | ICP fit score is 50% of total lead score (fit + behavior) |
| ABM tiering | Tier 1 → 1-to-1. Tier 2 → 1-to-few. Tier 3 → 1-to-many |
| Pipeline review | Flag deals below Tier 2 in pipeline review. Question whether sales time is justified |
| Forecasting | Weight pipeline by ICP tier. Tier 1 pipeline is more reliable than Tier 3 |
| Expansion targeting | Score existing customers. High-ICP customers are expansion candidates |

---

## Look-Alike Modeling

Use the ICP model to find new accounts that resemble your best customers.

### Process

```
1. Score your top 20 customers on all ICP dimensions
2. Calculate the average score profile:
   Size: 2.7, Industry: 3.0, Funding: 2.3, Geo: 3.0, Tech: 2.1
3. Search for accounts with similar profiles:
   Sales Nav, Apollo, or Crunchbase filtered to match each dimension
4. Score the results with the ICP model
5. Tier 1-2 matches become your look-alike target list
```

### Look-alike rules

- **Look-alikes from closed-won data, not from wishful thinking.** Model from your actual best customers, not from "the kind of company we wish would buy"
- **Update the look-alike profile quarterly.** As your customer base evolves, the "average best customer" profile changes. A profile from 12 months ago may not represent today's ICP
- **Look-alikes are a starting point, not a guarantee.** A company that looks like your best customer still needs a signal (timing) to become a real prospect. Look-alike + signal = qualified target. Look-alike alone = nurture

---

## Measurement

| Metric | Definition | Target | Frequency |
|--------|-----------|--------|-----------|
| Scoring coverage | % of accounts in CRM with an ICP score | > 90% | Monthly |
| Win rate by tier | Close rate for each ICP tier | Tier 1 should be 2x+ Tier 3 | Quarterly |
| Churn rate by tier | Churn rate for each tier | Tier 1 should be < 50% of Tier 3 | Quarterly |
| Pipeline concentration | % of pipeline from Tier 1-2 | > 70% | Monthly |
| Scoring accuracy | Do predictions match outcomes? | Track trend | Quarterly |
| Model drift | Have the best-performing segments shifted since last calibration? | Identify and update | Quarterly |

---

## Anti-Pattern Check

- Model built from intuition, not data. "I think mid-market SaaS is our ICP" is a hypothesis. "73% of closed-won deals are 51-200 employee SaaS companies" is a model. Use data
- No negative scoring. A government agency with 3 matching dimensions scores 45/100 and enters the pipeline. Without negative signals, bad-fit accounts pollute the pipeline. Add anti-ICP penalties
- Scoring but never using the score. The icp_score field exists in CRM but nobody looks at it. The score should drive routing, ABM tiering, lead scoring, and pipeline review. If it's not used, it's wasted
- Same model for 2 years. Markets shift. Products evolve. The ICP from 2 years ago may not predict today's best customers. Calibrate quarterly
- Over-weighting one dimension. "Industry is 60% of the score" because all your wins are in SaaS. But if 90% of your prospects are also SaaS, industry doesn't discriminate between fit and non-fit. Weight by predictive power (win-rate spread), not by frequency
- Scoring without enrichment data. 40% of accounts have blank industry and employee count fields. Their scores are wrong. Enrich first, score second