Skip to content
Open access

Graph-Based Features for Late-Delivery Risk Prediction in Supply Chains: A Leakage-Controlled Benchmark

2026 · International journal of research and scientific innovation · 0 citations

TL;DR

This study asks whether hand-crafted graph features, appended to a tabular XGBoost model, improve late-delivery risk prediction once leakage is controlled, and recommends order-grouped, temporal evaluation with a rule baseline.

Abstract

Predicting whether an order will be delivered late is a core task in supply chain analytics, and the public DataCo Smart Supply Chain dataset is widely used as a benchmark for it. Graph-based features and models are increasingly proposed to improve such predictions, but the dataset contains columns that leak the label and rows that share an order, which can inflate reported performance. This study asks whether hand-crafted graph features, appended to a tabular XGBoost model, improve late-delivery risk prediction once leakage is controlled. We audit the dataset, remove cancelled and fraud orders, and collapse 180,519 item rows into 62,897 orders. We build a heterogeneous graph of customers, products, categories, cities, countries and regions (24,268 nodes, 165,059 edges) with NetworkX, derive structural features, spectral embeddings and fold-safe label-aware encodings (a form of target encoding over graph neighbours), and evaluate them with XGBoost under order-level repeated cross-validation, a temporal split, Holm-corrected paired tests and SHAP. Leakage matters: a leaky column gives an AUC of 1.00, and a random row split overstates AUC by 0.024 (0.7985 versus 0.7749). Without leakage, the label is governed almost entirely by shipping mode and, for Same Day orders, by whether the order is placed after noon. A four-line lookup rule reaches an AUC of 0.774, and Standard and Second Class outcomes are indistinguishable from chance for every model (within-mode AUC about 0.50). Graph features add a nominal 0.003 AUC over XGBoost (uncorrected p = 0.049) that does not survive Holm correction (p = 0.146), cannot be distinguished from the rule (0.001, p = 0.445), and reverses on a temporal split (-0.005 against the rule). Entity-level late rates do not differ from shuffled labels. On DataCo, hand-crafted graph features therefore add no reliable signal; end-to-end graph neural networks were not tested. The whole graph pipeline costs about 5 s and under 1 GB of memory, so the problem is absence of signal, not cost. We recommend order-grouped, temporal evaluation with a rule baseline.

Read PDF

Similar papers

Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach

A heterogeneous graph patch transformer that forecasts quarterly changes in supply chain stress one and two quarters ahead can help supply chain managers and investors act before disruptions appear in reported financials.

Jianna Hur, Sagar Samtani · 0 citations
#graph neural networks Open access Sep 2026

Analyzing and Mitigating Asymmetric Learning for Product Cold-Start in E-Commerce Purchase Prediction with Graph Neural Networks: Similarity-Driven History Augmentation

This paper proposes Similarity-Driven History Augmentation (SHA), a data-centric approach that assigns synthetic interaction histories to cold-start products by matching them with semantically similar established donors and introduces a decoupled hybrid framework alongside an enhanced SHA strategy that selectively filt...

Imad Eddine Khiloun, Karima Belmabrouk, Latifa Dekhici et al. · 0 citations
Open access Oct 2026

SG-Net: A Spatiotemporal Graph Neural Network for Next-Step Supply-Chain Risk Monitoring via Demand Forecasting, Anomaly Detection, and Product-Relation Classification

This study introduces SG-Net, a spatiotemporal graph neural network that combines a relation-aware spatial encoder, a memory-augmented temporal encoder, and attention-based fusion that achieves the strongest mean performance across the four benchmark tasks.

A. Salamai, W. Zogaan · 0 citations
Conference Open access Sep 2026

Frequency-Enhanced Retrieval-Augmented Wide Stacking for Supply-Chain Credit Risk Prediction

Credit risk prediction in supply-chain finance is hard because the risk of a core enterprise is shaped not only by its own financials but also by the long-cycle operating conditions of its upstream suppliers. Conventional credit scoring models treat the task as static tabular classification, whereas time-series models...

Hong-Wei Zhang · 0 citations
Open access Oct 2026

TensorLock: Recovering Model Dependency for Model Supply Chain

This work proposes a novel model dependency recovering framework Tensorlock, which substantially outperforms state-of-the-art approaches in clustering and dependency identification, and applies it to 289 supposedly isolated models and recover 189 previously missing model dependencies.

Su-Sheng Wu, Zi-Qian Chen, Cheng-Yuan Li et al. · 0 citations
Open access Nov 2026

CF-TGNN: Counterfactual Explainable Temporal Graph Neural Networks for Supply Chain Disruption Prediction

Disruptions in multi-tier supply chains travel from upstream suppliers to downstream customers, and a risk model helps planners only if it can say what would have prevented a predicted disruption. Temporal graph neural networks with supplier attention forecast such ripple effects well, but attention weights are normali...

C. Chandra, Theo Adler · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.