v9ai/salescue-icp-v1

SalesCue — icp

WassersteinICPMatcher module from the SalesCue sales intelligence library.

Status: untrained — architecture only, random initialization. Use as a starting point for fine-tuning.

Research Contribution

Wasserstein Distance ICP Matching

Cosine similarity treats both ICP and prospect as point vectors, but an ICP like "100-500 employees" represents a range, not a point. WassersteinICPMatcher models the ICP as a Gaussian distribution in embedding space and the prospect as a point, then computes the Wasserstein distance (earth mover's distance) between them. Per-dimension projections (industry, size, tech, role, signal) with learned dealbreaker thresholds provide interpretable matching with explicit disqualification reasons.

Usage

from salescue import SalesCueModel

model = SalesCueModel.from_pretrained("v9ai/salescue-icp-v1")
result = model.predict('{"icp": "Mid-market SaaS companies", "prospect": "300-person fintech startup"}')
print(result)  # score, qualified, dimensions, dealbreakers

Labels

• industry
• size
• tech
• role
• signal

Architecture

• Backbone: microsoft/deberta-v3-base (shared encoder, 768-dim)
• Head: WassersteinICPMatcher
• Parameters: head only (backbone loaded separately)

Intended Use

• Primary: B2B sales intelligence — lead scoring, email analysis, conversation insights
• Users: Sales teams, RevOps, GTM engineers building sales automation
• Input: English sales text (emails, call transcripts, prospect communications)

Limitations

• Untrained weights: This release contains the architecture only. Weights are randomly initialized and must be fine-tuned on domain-specific data before production use.
• English only: Designed for English sales text. Performance on other languages is untested.
• Domain-specific: Optimized for B2B sales communications. May not generalize to other text domains.
• Shared backbone: Requires microsoft/deberta-v3-base loaded via the SalesCue library.

About SalesCue

SalesCue is a sales intelligence library with 12 ML modules sharing a single DeBERTa-v3-base encoder backbone. Modules can be composed via Unix-style piping:

from salescue import Document
result = Document("interested in pricing") | ai.score | ai.intent | ai.sentiment

All modules: score intent reply triggers icp objection sentiment spam entities call subject emailgen

See the SalesCue documentation for details.