{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T04:29:26Z","timestamp":1780720166008,"version":"3.54.1"},"reference-count":26,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Financial institutions increasingly rely on data-driven decision systems; however, many operational models remain purely predictive, failing to account for confounding biases inherent in observational data. In credit settings characterized by selective treatment assignment, this limitation can lead to erroneous policy assessments and the accumulation of \u201cmethodological debt\u201d. To address this issue, we propose an \u201cEstimate \u2192 Predict &amp; Evaluate\u201d framework that integrates Double Machine Learning (DML) with practical MLOps strategies. The framework first employs DML to mitigate selection bias and estimate unbiased Conditional Average Treatment Effects (CATEs), which are then distilled into a lightweight Target Model for real-time decision-making. This architecture further supports Off-Policy Evaluation (OPE), creating a \u201cCausal Sandbox\u201d for simulating alternative policies without risky experimentation. We validated the framework using two real-world datasets: a low-confounding marketing dataset and a high-confounding credit risk dataset. While uplift-based segmentation successfully identified responsive customers in the marketing context, our DML-based approach proved indispensable in high-risk credit environments. It explicitly identified \u201cSleeping Dogs\u201d\u2014customers for whom intervention paradoxically increased delinquency risk\u2014whereas conventional heuristic models failed to detect these adverse dynamics. The distilled model demonstrated superior stability and provided consistent inputs for OPE. These findings suggest that the proposed framework offers a systematic pathway for integrating causal inference into financial decision-making, supporting transparent, evidence-based, and sustainable policy design.<\/jats:p>","DOI":"10.3390\/systems14010016","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T09:58:34Z","timestamp":1766570314000},"page":"16","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Prescriptive Analytics for Sustainable Financial Systems: A Causal\u2013Machine Learning Framework for Credit Risk Management and Targeted Marketing"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0651-3050","authenticated-orcid":false,"given":"Jaeyung","family":"Huh","sequence":"first","affiliation":[{"name":"College of Business and Economics, Sejong University, Seoul 05006, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.ins.2019.12.075","article-title":"Why you should stop predicting customer churn and start using uplift models","volume":"548","author":"Devriendt","year":"2021","journal-title":"Inf. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1509\/jmr.16.0163","article-title":"Retention futility: Targeting high-risk customers might be ineffective","volume":"55","author":"Ascarza","year":"2018","journal-title":"J. Mark. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_4","unstructured":"Lee, S.H., Jang, D.J., and Cho, C.K. (2022). Method and Device for Selecting Promotion Targets. (Korean Patent No. 10-2414960)."},{"key":"ref_5","unstructured":"Kiyohara, H., Kishimoto, R., Kawakami, K., Kobayashi, K., Nakata, K., and Saito, Y. (2023). Towards assessing and benchmarking risk\u2014Return tradeoff of off-policy evaluation. arXiv."},{"key":"ref_6","unstructured":"Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., and Vaughan, J.W. (2021). Universal off-policy evaluation. Advances in Neural Information Processing Systems 34, Curran Associates, Inc."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Pearl, J. (2009). Causality: Models, Reasoning, and Inference, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/CBO9780511803161"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies","volume":"66","author":"Rubin","year":"1974","journal-title":"J. Educ. Psychol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cho, R., Desbordes, R., and Eberhardt, M. (Oxf. Bull. Econ. Stat., 2025). The economic effects of \u201cexcessive\u201d financial deepening, Oxf. Bull. Econ. Stat., Online First.","DOI":"10.1111\/obes.70018"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s11129-023-09278-5","article-title":"Heterogeneous treatment effects and optimal targeting policy evaluation","volume":"22","author":"Hitsch","year":"2024","journal-title":"Quant. Mark. Econ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4156","DOI":"10.1073\/pnas.1804597116","article-title":"Metalearners for estimating heterogeneous treatment effects using machine learning","volume":"116","author":"Kunzel","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"113648","DOI":"10.1016\/j.dss.2021.113648","article-title":"Uplift modeling with value-driven evaluation metrics","volume":"150","author":"Gubela","year":"2021","journal-title":"Decis. Support. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"320","DOI":"10.3934\/DSFE.2025014","article-title":"Comparative Analysis of Classical and Bayesian Optimisation Techniques: Impact on Model Performance and Interpretability in Credit Risk Modelling Using SHAP and PDPs","volume":"5","author":"Shoko","year":"2025","journal-title":"Data Sci. Financ. Econ."},{"key":"ref_14","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30, Curran Associates, Inc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"C1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov","year":"2018","journal-title":"Econom. J."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chuang, H.-C., and Chen, J.-E. (2023). Exploring industry-distress effects on loan recovery: A double machine learning approach for quantiles. Econometrics, 11.","DOI":"10.3390\/econometrics11010006"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3905\/jfds.2025.1.187","article-title":"Deciphering the causal drivers of bond indexes: A double machine learning approach","volume":"7","author":"Sadeghi","year":"2025","journal-title":"J. Financ. Data Sci."},{"key":"ref_18","first-page":"1","article-title":"How does structural monetary policy affect traditional bank lending?","volume":"30","author":"Wang","year":"2025","journal-title":"J. Asia Pac. Econ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1093\/biomet\/asaa076","article-title":"Quasi-oracle estimation of heterogeneous treatment effects","volume":"108","author":"Nie","year":"2021","journal-title":"Biometrika"},{"key":"ref_20","first-page":"1","article-title":"Real-time risk management plan for revolving credit products based on new delinquency rates","volume":"20","author":"Huh","year":"2025","journal-title":"J. Korean Innov. Soc."},{"key":"ref_21","unstructured":"Huh, J., and Kim, J. (2025). Heterogeneous Causal Effects of Credit Policy in Confounded Financial Environments. manuscript in preparation."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1214\/ss\/1009213726","article-title":"Statistical modeling: The two cultures","volume":"16","author":"Breiman","year":"2001","journal-title":"Stat. Sci."},{"key":"ref_23","unstructured":"Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., and Garnett, R. (2015). Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems 28, Curran Associates, Inc."},{"key":"ref_24","first-page":"3230","article-title":"The real impact of FinTech: Evidence from mobile payment technology","volume":"69","author":"Agarwal","year":"2023","journal-title":"Manag. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7902","DOI":"10.71097\/IJSAT.v16.i3.7902","article-title":"Fairness-Constrained Collections Policies: A Theoretical Model with Off-Policy Evaluation","volume":"16","author":"Gupta","year":"2025","journal-title":"Int. J. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1111\/rssb.12348","article-title":"Making sense of sensitivity: Extending omitted variable bias","volume":"82","author":"Cinelli","year":"2020","journal-title":"J. R. Stat. Soc. Ser. B"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/16\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T10:23:19Z","timestamp":1766571799000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010016"],"URL":"https:\/\/doi.org\/10.3390\/systems14010016","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]}}}