Paper: arXiv 2510.05487
Authors: Jinho Cha, Sahng-Min Han, Long Pham
Abstract
Effective supply chain management under high-variance demand requires models that jointly address demand uncertainty and digital contracting adoption. Existing research often simplifies demand variability or treats adoption as an exogenous decision, limiting relevance in e-commerce and humanitarian logistics. This study develops an optimization framework combining dynamic Negative Binomial (NB) demand modeling with endogenous smart contract adoption. The NB process incorporates autoregressive dynamics in success probability to capture overdispersion and temporal correlation. Simulation experiments using four real-world datasets, including Delhivery Logistics and the SCMS Global Health Delivery system, apply maximum likelihood estimation and grid search to optimize adoption intensity and order quantity. Across all datasets, the NB specification outperforms Poisson and Gaussian benchmarks, with overdispersion indices exceeding 1.5. Forecasting comparisons show that while ARIMA and Exponential Smoothing achieve similar point accuracy, the NB model provides superior stability under high variance. Scenario analysis reveals that when dispersion exceeds a critical threshold (r > 6), increasing smart contract adoption above 70% significantly enhances profitability and service levels. This framework offers actionable guidance for balancing inventory costs, service levels, and implementation expenses, highlighting the importance of aligning digital adoption strategies with empirically observed demand volatility.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced statistical modeling (Negative Binomial with autoregressive dynamics, maximum likelihood estimation, grid search optimization) and validates the framework using four real-world datasets with forecasting comparisons and scenario analysis.
Research Flowchart
flowchart TD A["Research Goal: Optimize smart contract adoption under high-variance demand"] --> B["Methodology: Dynamic NB Demand Modeling with Endogenous Adoption"] B --> C["Data: Four real-world datasets<br>Delhivery Logistics, SCMS Global Health, etc."] C --> D["Computations: MLE, Grid Search,<br>Scenario Analysis"] D --> E["Findings: NB outperforms benchmarks<br>Adoption >70% boosts profit when dispersion >6"] A --> E
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes an optimization framework that combines dynamic Negative Binomial demand modeling with endogenous smart contract adoption for supply chain management.
Source sentence
This study develops an optimization framework combining dynamic Negative Binomial (NB) demand modeling with endogenous smart contract adoption.
Assumes 3
- Demand follows a Negative Binomial distribution with autoregressive dynamics in the success probability. statistical
Source sentence
Assumptions: Demand follows a Negative Binomial distribution with autoregressive dynamics in the success probability.
- Suppliers differ in digital readiness, which affects procurement costs. model
Source sentence
Suppliers differ in digital readiness, which affects procurement costs.
- The retailer optimizes expected profit under holding costs, stockout penalties, variance penalties, service level penalties, and risk aversion considerations. model
Source sentence
The retailer optimizes expected profit under holding costs, stockout penalties, variance penalties, service level penalties, and risk aversion considerations.
Data
- Global Superstore other public
Source sentence
Global Superstore International 2011–2014 51,290 Quantity, Unit Price, Ship Date
- E-Commerce Orders other public
Source sentence
E-Commerce Orders India 2019–2020 65,000 Order Date, Quantity, Lead Time
- Delhivery Logistics other public
Source sentence
Delhivery Logistics India 2018 148,170 Trip Dates, Route Type, Delay Days
- SCMS Delivery History other public
Source sentence
SCMS Delivery History Global 2015–2017 9,215 Order Volume, Delivery Costs, Delays
Costs
Not applicable
Finds 5
- The Negative Binomial specification outperforms Poisson and Gaussian benchmarks across all datasets. performance
Source sentence
Across all datasets, the NB specification outperforms Poisson and Gaussian benchmarks, with overdispersion indices exceeding 1.5.
- The NB model provides superior stability under high variance compared to ARIMA and Exponential Smoothing. predictive-accuracy
Source sentence
while ARIMA and Exponential Smoothing achieve similar point accuracy, the NB model provides superior stability under high variance.
- When dispersion exceeds a critical threshold (r > 6), increasing smart contract adoption above 70% significantly enhances profitability and service levels. performance
Source sentence
Scenario analysis reveals that when dispersion exceeds a critical threshold (r > 6), increasing smart contract adoption above 70% significantly enhances profitability and service levels.
- Expected profit improves steadily as smart contract adoption intensity increases. performance
Source sentence
clear and steady improvement in profitability as adoption intensity increases.
- Negative Binomial regression achieves the lowest MAE (1,354.52) and MAPE (22.36%) among compared forecasting models on the SCMS dataset. predictive-accuracy
Source sentence
As illustrated in Figure 10, the Negative Binomial model consistently outperformed alternative approaches, achieving the lowest Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE).
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 65 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.