{"paper_id":"2506.22711","title":"Potential Customer Lifetime Value in Financial Institutions: The Usage Of Open Banking Data to Improve CLV Estimation","authors":["João B. G. de Brito","Rodrigo Heldt","Cleo S. Silveira","Matthias Bogaert","Guilherme B. Bucco","Fernando B. Luce","João L. Becker","Filipe J. Zabala","Michel J. Anzanello"],"paper_date":"2025-06-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2506.22711v1","page_url":"https://thequant.space/flowcharts/potential-customer-lifetime-value-in-financial-institutions/","scores":{"empirical_rigor":7.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes the Potential Customer Lifetime Value (PCLV) framework that uses Open Banking data to estimate customer value beyond a single institution.","quote":"This study introduces the Potential Customer Lifetime Value (PCLV) framework, leveraging Open Banking (OB) data to estimate customer value comprehensively.","summary":"Financial institutions increasingly adopt customer-centric strategies to enhance profitability and build long-term relationships. While Customer Lifetime Value (CLV) is a core metric, its calculations often rely solely on single-entity data, missing insights from customer activities across multiple…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A 12‑month prediction horizon is used for PCM and PCLV calculations.","type":"model","stated":"explicit","quote":"assuming a prediction horizon of 12 months, as presented in Eq. 5."},{"assumption":"An annual discount rate of 0.1 is applied in PCLV valuation.","type":"model","stated":"explicit","quote":"A 0.1 annual discount rate was applied, with monetary values converted to USD at R$4.8521/$1 on Dec 31, 2023."},{"assumption":"PCM for the next 12 months is projected by multiplying the predicted monthly PCM by 12, assuming the last training month’s PCM persists.","type":"model","stated":"explicit","quote":"Multiplying the PCM by 12 projects the estimated monthly PCM over the next 12 months, assuming the PCM from the last training month, reasonably predicts the upcoming year's value."},{"assumption":"Only customers who share OB data can have PCM and PCLV predicted.","type":"data","stated":"explicit","quote":"only 10,507 customers (0.32%) shared OB data, enabling PCM and PCLV predictions exclusively for these customers."}]},"datasets":{"status":"available","items":[{"name":"Brazilian bank credit‑related PSC dataset","provider":"major Brazilian bank","kind":"alternative","access":"proprietary","period":"Jan 2021–Dec 2023","universe":"3,335,034 customers, 261 million transactions","quote":"A 36-month dataset (Jan 2021–Dec 2023) covering 261 million transactions for 3,335,034 customers was processed for churn prediction"},{"name":"Open Banking competitor credit data","provider":null,"kind":"alternative","access":"unknown","period":"Dec 2023","universe":"10,507 customers who shared OB data","quote":"However, only 10,507 customers (0.32%) shared OB data, enabling PCM and PCLV predictions exclusively for these customers."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The churn prediction model achieved a PR‑AUC of 0.96, sensitivity 0.88, specificity and accuracy of 0.92.","kind":"predictive-accuracy","quote":"Using 10-fold cross-validation, it achieved a PR-AUC of 0.96, sensitivity of 0.88, and specificity and accuracy of 0.92."},{"finding":"The XGBoost regression model for PCM prediction yielded a mean RMSE of $74 and MAE of $11.13.","kind":"predictive-accuracy","quote":"resulting in a mean RMSE of $74 and MAE of $11.13, demonstrating its predictive accuracy."},{"finding":"Potential Customer Lifetime Value (PCLV) provides an estimated upside of 21.06% over Actual CLV.","kind":"performance","quote":"Results show that OB data can be used to estimate PCLV per competitor, indicating a potential upside of 21.06% over the Actual CLV."}],"reported_performance":null,"out_of_sample":{"method":"cross-validation","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:34:24Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}