Pricing ML / Demand · Independent project

Marketplace Intelligence: Pricing, Demand and Sale Probability

Author: Dmitri Derevjanko · Tallinn, Estonia · 2025-12 · updated 2026-08

Dmitri Derevjanko built Marketplace Intelligence, a six-model pricing and demand system that recommends listing prices, estimates sale probability, and shows the training data behind each decision.

This is one of 10+ independent public projects by Dmitri Derevjanko. 100+ additional workflows were delivered professionally, mostly under confidentiality, and are not documented here.

Marketplace Intelligence dashboard with price recommendation and model metrics
Marketplace Intelligence — live system built by Dmitri Derevjanko.

Open live demo Back to portfolio

Problem

Marketplace pricing work often lives in notebooks: one model for price, another for demand, no comparable listings, and no way for a non-ML user to see why a number appeared. Isolated metrics do not help someone set a listing price.

Solution

One FastAPI and React product where pricing, sale probability, demand forecasts, comparable retrieval, funnel diagnostics, and explainability share a single workflow, with production-facing champions labelled separately from weaker diagnostic modules.

What Dmitri Derevjanko built

Dmitri trained and evaluated the models, chose champions on validation metrics, built the API contracts, the SaaS-style dashboard, training-data preview, what-if simulations, Docker demo startup, and regression tests. The public demo is his independent system, not a client case study.

Architecture

  1. Mercari listings feed a hybrid Ridge/router pricing champion over 1.47M searchable comparables (validation RMSLE 0.4157, MAE 8.4999).
  2. MerRec behavioural events train a blended LightGBM sale-probability model on a 5M-event sample (ROC-AUC 0.8797).
  3. Olist category-month series drive demand forecasts (R2 0.9048, WMAPE 24.35%).
  4. Comparable retrieval explains a recommended price with real similar listings, not only a score.
  5. MLflow artifacts, health views, and dataset lineage sit next to the user-facing analysis screens.
  6. Docker Compose starts backend, frontend, and artifacts together for a repeatable demo.

Technologies

Result

A demo-ready marketplace ML product: six cooperating models, real training-data inspection, what-if pricing, and honest confidence labels for sparse funnel stages.

Limitations

Live demo and source

Live demo: https://pricingiq.dmitriderevjanko.com/

GitHub: source is not public. The live demo is the public artifact for this project.

Portfolio case study: https://dmitriderevjanko.com/projects/marketplace-intelligence/

Other independent projects by Dmitri Derevjanko