Dynamic yield pricing for perishable equipment inventory

Arkham · Real-Time Pricing & Yield Management

Download paper

Data-T Research presents Arkham — a dynamic pricing and yield management engine that applies airline and hotel revenue-management science to equipment rentals. Reinforcement learning, stochastic dynamic programming, and spot auctions continuously clear laser cleaning fleets and related asset classes.

0009-0009-2205-533XMuskan SharmaYield Mesh 1.0
Fleet revenue lift
+29.6%
Projected annual revenue vs static rates
Utilisation
+16 pp
62% → 78% average fleet utilisation
Quote TTL
~90 s
Signed, non-transferable market quotes
Pricing engines
3
RL · SDP contracts · spot auction

Our work

Dynamic Yield Pricing: Real-Time Dynamic Pricing and Yield Management for Laser Cleaning Equipment Leasing

Research Paper
Muskan Sharma · Data-T Research Org · Arkham Research Report

Static rental rates leave willingness-to-pay uncaptured at peaks and idle inventory at troughs. Arkham closes the information gap by ingesting demand and supply signals, then clearing market prices through RL elasticity agents, SDP forward contracts, and a real-time spot auction — with short-lived auditable quotes that prevent hold-and-wait arbitrage.

Yield ManagementEquipment LeasingReinforcement Learning

Program architecture — quote request to market-clearing price

Figure 1
RL · SDP · auction · revenue and audit path
ArchitectureAPI

Operator surfaces — customer, partners, and API docs

Product
Quote → reserve → confirm → track → release
ArkhamDashboards
Open access archive on ZenodoRead more research on our hub

Results & figures

Table 1. Projected fleet performance with Arkham versus static pricing
MetricStaticArkhamImprovement
Average utilisation62%78%+16 pp
Avg. revenue per machine-hour$18.50$21.30+15.1%
Total annual fleet revenue$1,620,000$2,100,000+29.6%
Booking satisfaction rate74%91%+17 pp
Table 2. Core Arkham API endpoints
MethodPathPurpose
GET/fleet/machinesCatalogue and status
GET/fleet/summaryAvailability and utilisation
POST/pricing/quoteSigned time-limited quote
POST/booking/confirmConfirm booking
GET/booking/{id}/trackDelivery tracking
POST/booking/{id}/completeEnd service / release
Arkham program architecture from quote request through pricing engines to audit
Figure 1. Program architecture for Arkham dynamic pricing: quote request, pricing engines (RL, SDP, auction), market-clearing price, and revenue/audit path.
Arkham operator dashboard surfaces
Figure 2. Operator surfaces — sign-in, customer estimator, partners console, API docs, internal ops, and architecture/business views.
Arkham business model overview
Figure 3. Business model overview — revenue streams, strategic partners, platform modules, and operating cost classes.
Arkham business overview diagram
Figure 4. End-to-end business overview used in the Dynamic Yield Pricing research programme.
Arkham program process flow
Figure 5. Program process map — fleet signals, pricing clearance, booking lifecycle, and release.

Open access · Dynamic Yield Pricing Research

Muskan Sharma · Data-T · doi:10.5281/zenodo.21873050 · Arkham yield management · Borel Sigma Inc. venture

Download full report

Tools + Code

Research Paper

Dynamic Yield Pricing — research report on real-time pricing and yield management for laser cleaning equipment leasing.

View project

Yield Mesh 1.0

Live pricing console — customer booking, internal ops, fleet quotes, tracking, and release via /api/yieldmesh.

View project

Dynamic-Yield-Pricing

Open source FastAPI pricing engine, RL training stack, and operator UI sources.

View project

Manuscript PDF

Full Dynamic_Yield_Pricing.pdf with architecture figures, fleet catalogue, and projected benefit tables.

View project

Open access

Source program, operator media, diagrams, and the manuscript are published for public reuse. Persistent identifier doi:10.5281/zenodo.21873050. Code on GitHub. Live portal at arkham.q-dit.com.

ORCID · 0009-0009-2205-533XMuskan Sharma