Pharma Account Prospecting - Data-Driven Lead Generation

Pharma Account Prospecting - Data-Driven Lead Generation

Clinical trial data and public filings converted into prioritized account lists with executive contact information.


Book a 15-min consult

Book a 15-min consult

Impact & Deliverables

Situation: Sales/prospecting teams needed a defensible way to prioritize emerging pharma accounts from noisy public sources, unverified research sites, and scattered trial activity—without manual research or bloated vendor databases.

What I built: Automated prospecting system extracting clinical trial data from ClinicalTrials.gov. Multi-factor scoring model evaluating emerging pharma companies on financial metrics, team composition, and pipeline activity. Prioritized account list delivered with executive contacts and composite scores for sales targeting.
Outcome: Faster, defensible targeting with testable weighting and filters (by vertical, geography, or funding stage), easy refresh cadence, and portfolio visibility.

Trials Data Pull
Normalize & Clean
Phase/Recency Filter
Add Financial Signals
Score Companies
Prioritize & Segment
Map Executives
Outreach List (CSV/CRM)
Trials Data PullNormalize & CleanPhase/Recency FilterAdd Financial Signals
Score CompaniesPrioritize & SegmentMap ExecutivesOutreach List (CSV/CRM)

Workflow

Workflow

Workflow

Trials Data PullNormalize & CleanPhase/Recency FilterAdd Financial Signals
Score CompaniesPrioritize & SegmentMap ExecutivesOutreach List (CSV/CRM)

Consulting Relevance

Converts manual prospecting into automated, repeatable lead generation. Extracts clinical trial and financial data, applies custom scoring logic, and delivers prioritized account lists with executive contacts. Output integrates with existing CRM systems via CSV export.

Data Pipeline & Scoring Architecture
Clinical trial extraction, feature engineering, multi-factor scoring, and prioritized account delivery.
Data Sources & Processing
Source data
ClinicalTrials.gov records extracted for sponsor name, trial phase, completion dates, and therapeutic indications. Focused on active development signals.
Scope & filters
U.S. and target geographies with Phase II/III emphasis. Recent completions and active studies prioritized. Sponsor name deduplication and canonicalization applied.
Data governance
Public endpoints only with documented access patterns. Source URLs and version timestamps maintained for audit trail.
Output
Normalized sponsor-level dataset with trial metadata ready for feature engineering and scoring.
Feature Engineering & Scoring
Feature Development
Sponsor standardization
Name canonicalization with cross-trial deduplication. Alias mapping maintained with source URL references.
Trial activity metrics
Calculated recency windows, active study counts, and phase distribution (Phase II vs III) by indication area.
Financial signals
Operating costs, revenue, operational efficiency ratios. Normalized for cross-company comparison.
Scoring Model
Scoring dimensions
Operational efficiency, sales and pipeline focus, pipeline depth (drug and indication counts).
Calculation method
Input standardization with weighted combination into composite scores. Outlier flagging with adjustable weights by vertical or development stage.
Output format
Ranked company list with composite scores, scoring rationale columns, and outreach context notes.
Delivery & Maintenance
Export format
CRM-ready CSV with ranked targets, segment classifications, and scoring component breakdowns.
Executive contacts
CEO, CFO, CCO, and BD roles sourced from public filings, company websites, and LinkedIn profiles.
Segmentation
Account groupings by phase mix, trial recency, and efficiency profiles for targeted outreach campaigns.
Update cadence
Monthly or quarterly refresh cycles: trial data re-extraction, feature recalculation, scoring updates, and change logging.
Data Governance & Operations
Public data sources only with no sensitive PII collection. Executive contacts sourced from public records. Source URLs, version stamps, and refresh logs maintained for audit trail. Scoring weights and filter criteria documented for defensibility.

Open to short consults and build sprints.

Book a 15-min consult

© 2022–2025 Matt Tunison. All rights reserved.

Book a 15-min consult

Open to short consults and build sprints.

Open to short consults and build sprints.

© 2022–2025 Matt Tunison. All rights reserved.