American Journal of Business and Operations Research

Maintenance-economic studies often convert condition indicators into apparent costs without verifying whether the resulting targets are independent of the model inputs. This can produce exceptionally high but operationally misleading accuracy. We formulate component-level estimation for a COmbined Diesel-eLectric And Gas (CODLAG) propulsion plant as a leakage-resistant digital-shadow problem. The primary dataset is the public UCI naval propulsion dataset: 11,934 steady-state observations generated by a calibrated numerical frigate simulator across nine speed settings, 51 compressor-health states, and 26 turbine-health states. Because it contains neither monetary maintenance records nor live vessel telemetry, the outputs are explicitly defined as dimensionless compressor and turbine cost-risk indices rather than currency costs. Health coefficients and every target-derived quantity are excluded from predictors. Models are tuned by three-fold grouped inner validation and assessed by five-fold outer validation in which all observations sharing a degradation pair remain in the same fold. Extra Trees achieved an aggregate cost-risk RMSE of 0.0222 (95% CI half-width 0.0049) and R2 of 0.9886 (95% CI half-width 0.0049) under nominal interpolation. However, combined noise, missingness, calibration bias, and channel loss reduced R2 to 0.6335 even after corruption-augmented training, while leave-one-speed-regime-out testing produced mean R2 = −0.379. Scenario-matched 90% split-conformal intervals retained 89.5–90.4% empirical coverage by widening from 0.032 nominally to 0.406 under severe corruption. An external NASA C-MAPSS FD001 benchmark yielded RMSE 16.97 cycles and R2 = 0.821 for remaining-useful-life prediction on 100 unseen engines. The study therefore supports robust condition-risk ranking within the simulated envelope, not direct monetary forecasting or autonomous maintenance scheduling. The principal contribution is a transparent validation protocol that exposes target leakage, simulator determinism, sensor-quality sensitivity, and the boundary between a digital shadow and a deployable digital twin.

Credit score explanations can influence lending reviews, exception handling, and customer communication, yet an explanation may change under resampling, recommend an infeasible action, or fail to illuminate the approval decision. This structured review examines the evidence needed to use explanations in lending and risk management. Thirty-eight journal studies published from 2023 through January 2026 were coded by method family, information setting, validation design, and decision connection. The evidence spans interpretable scores and rules, post hoc attributions, counterfactuals, stability tests, fairness audits, and decision-oriented comparators. It does not support a single ranking of methods: studies examine different properties on different applicant populations, and few identify the incremental effect of an explanation on an underwriter’s action or an applicant’s outcome. Four comparisons organize the findings. Predictive discrimination does not establish explanation fidelity; plausible local reasons may not survive changes in training data; a score-changing counterfactual may be unattainable; and similar attributions do not imply equal lending outcomes. We develop a validation framework linking temporal performance, explanation perturbations, feasible action, group analysis, and policy value. Additional analyses map the evidence to decision stages, distinguish estimable quantities from missing outcomes, and specify reporting standards for management use. The review contributes an operational basis for deciding when an explanation can be treated as evidence in underwriting rather than as a model display.

Retail analytics has moved beyond improving point forecasts, yet evidence about the value of a forecast for pricing, replenishment, fulfillment, and managerial adoption remains dispersed. This structured review compares 36 journal studies published from 2023 through 2025, identified within a search window ending in January 2026, across four connected areas: demand forecasting (12), pricing and commercial levers (7), inventory and fulfillment (8), and decision systems (9). Each study is examined for its information setting, analytic approach, decision connection, and evidence boundary. The synthesis identifies four recurring discontinuities: sales data can conceal unmet demand; forecast scores can misrank policies; a policy that works in a model may be infeasible in a distributed retail organization; and staff may override recommendations whose value has not been made legible. A decision-centered evaluation structure links data availability, uncertainty estimation, feasible action, adoption, and realized economic outcomes. The paper develops a research agenda around observable-demand corrections, decision-calibrated uncertainty, joint pricing and fulfillment, transportable evaluations, and human-in-the-loop deployment. The review is deliberately bounded rather than a claim of exhaustive coverage or pooled effect sizes. It offers business intelligence researchers a common basis for studying whether analytical improvements survive the operational decisions they are meant to inform.

Complaint dashboards often pool unlike cases and report an overall resolution rate. For a financial-services operations team, that average can conceal which issues account for redress workload and whether a triage signal remains useful on later cases. We analyze 75,988 publicly reported U.S. credit-card complaints received in 2024. The outcome is the company’s recorded “closed with monetary relief” category, not a verified payment amount or customer satisfaction. Intake issue, sub-issue, submission channel, and company identify a transparent logistic screening model trained on January–September records and evaluated on October–December records. Report-related issues comprise 31.9%of complaints but have a 0.63% monetary-relief rate, compared with 19.16% for other issues. An exact shift-share decomposition attributes 1.81 of the 2.64 percentage points of decline from the first to fourth quarter to changing issue mix. Issue alone achieves an out-of-time area under the receiver operating characteristic curve (AUC) of 0.819; adding sub-issue and channel raises it to 0.831. A cross-company specification reaches 0.873 (95% bootstrap interval 0.867–0.878) and captures 39.4% of recorded monetary-relief responses in its highest-scoring tenth of holdout cases. The company term captures institutional and routing differences, so that result does not measure issuer quality or the gain attainable within a single firm. Case-mix-aware reporting and temporal validation support staffing review queues without automating redress decisions.

An international expansion team must decide which candidate markets warrant costly commercial due diligence. Regulation-only rankings can overlook the services and operating processes needed to conduct business. We develop a reproducible business intelligence screen using the three published pillars of the World Bank’s Business Ready 2025 for 101 economies. The analysis compares a regulation-led shortlist with a noncompensatory weakest-pillar rule, tests its sensitivity to shortlist capacity and alternative aggregation, and examines a mechanical one-pillar improvement scenario. Public Services is the lowest pillar in 67 economies and Operational Efficiency in 31. Regulation exceeds services by 12.36 points on average (95% bootstrap interval 10.52–14.12). The regulation-led and bottleneck-led top 20 share 11 economies, so nine due-diligence candidates change; their equal-weight and bottleneck-led counterparts share 18. Raising the lowest pillar hypothetically by ten points increases the resulting minimum by 6.63 points on average because another pillar may become binding. The output identifies markets requiring checks of service delivery or operational execution before a site-selection decision. Its rankings are transparent decision rules applied to official scores, not World Bank rankings, investment-return estimates, or evidence of causal reform effects.

A lender choosing markets for small-enterprise finance may use account ownership as a shortcut for credit demand. This article asks whether that shortcut identifies places where adults report borrowing to start or operate a business. We analyze the 2024 country estimates in the World Bank’s Global Findex Database 2025: 98 economies with complete business borrowing, account, formal-channel borrowing and formal saving measures. Account ownership and business borrowing are negatively associated across those economies (Spearman ρ = −0.220). An account-only model has a leave-one-economy-out mean absolute error of 5.529 percentage points, close to a constant forecast (5.580); adding formal-channel borrowing barely changes it. Adding formal saving reduces error to 4.700 points, although individual country errors remain substantial. Fifteen economies fall simultaneously above the sample’s upper quartile of business borrowing and below its median account ownership. In 40 economies with paired gender estimates, men have higher business borrowing in 19 and women in 21; account gender gaps do not reproduce a uniform enterprise-credit gap. These are country-level diagnostics of reported borrowing, not loan applications, unmet credit demand or evidence that account access causes enterprise borrowing. A staged market screen should therefore use purpose-specific borrowing and validate borrower quality and local lending rules before capital allocation.

Procurement teams often rank destination markets using a single published tariff average. Whether that ordering survives a change of measurement is a practical question for business intelligence. We audit the 2025 World Tariff Profiles, retaining 101 economies with matching 2024 most-favoured-nation (MFN) applied tariffs, reported trade-weighted tariffs, and 2023 import totals. A reproducible screen compares simple and trade-weighted averages, ranking changes, duty-free subheading shares, and the share of subheadings facing duties above 15%. The median simple average is 7.5% and the median trade-weighted average is 6.9%; the within-economy weighted-minus-simple median is −0.6 percentage points. Thirty-five economies differ by at least two points. With ties retained at each top-25 cutoff, 28 economies qualify under the simple rate and 26 under the weighted rate, but only 20 qualify under both. Türkiye falls from 17.3% to 7.0%, whereas Dominica rises from 10.7% to 15.9%. Disagreement persists among larger import markets: 13 of 31 economies with at least US$50 billion in 2023 imports have a gap of two points or more. A layered dashboard should therefore trigger product-level verification where aggregate measures disagree. Neither average identifies the duty paid by a particular firm or the effect of changing trade policy.