genpark-amazon-author-ranker

GenPark Amazon Author Ranker is a zero-dependency Amazon KDP publishing and BSR algorithmic analytics engine implementing power-law log-log daily sales velocity conversion models, front-loaded title keyword SEO relevance scoring, and rank decay half-life projection curves.

flowchart TD
    A[Amazon Best Sellers Rank BSR] --> B[Power-Law Log-Log Regression Model]
    B --> C[Daily & Monthly Unit Sales and Revenue]
    D[Book Title & Subtitle Tokens] --> E[Front-Loaded Keyword Scoring]
    E --> F[Amazon Search Relevance Index]
    G[Current Rank & Target BSR] --> H[Half-Life Inertia Decay Engine]
    H --> I[Promotional Burst Units Required]

Features

• BSR Sales Velocity Model: Maps category ranks to exact daily unit velocities and monthly revenue using empirical power-law formulas.
• Title SEO Keyword Scoring: Evaluates front-loaded title positioning, subtitle coverage, and search index density.
• Ranking Decay Half-Life: Projects natural rank slippage and quantifies the exact promotional sales volume needed to breach bestseller thresholds.

Quickstart

from client import GenParkAmazonAuthorRanker

ranker = GenParkAmazonAuthorRanker()
res = ranker.estimate_daily_sales_velocity_from_bsr(1000, "books")
print("Daily Units:", res["estimated_daily_sales_units"])

License

MIT