{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:31:09Z","timestamp":1750221069909,"version":"3.41.0"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2018,7,25]],"date-time":"2018-07-25T00:00:00Z","timestamp":1532476800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003845","name":"Indian Institute of Technology Madras","doi-asserted-by":"crossref","award":["Robert Bosch Centre for Data Science and Artificial Intelligence"],"award-info":[{"award-number":["Robert Bosch Centre for Data Science and Artificial Intelligence"]}],"id":[{"id":"10.13039\/501100003845","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMIS Database"],"published-print":{"date-parts":[[2018,7,25]]},"abstract":"<jats:p>There is a growing interest in understanding, as opposed to predicting, the repayment behavior of customers of financial institutions that provide loans. This study proposes a modified Hidden Markov Model (HMM) based clustering, which clusters repayment sequences across selected subsets of the HMM parameters. We demonstrate that different implementations of this modified adaptation helps us gain an in-depth understanding of various drivers that are hard to directly observe but nevertheless govern repayment. These include drivers such as the ability to repay (financial health of the customer) or the intention to repay independent of the ability (willful defaulting and unintentional delinquency). Algorithmically, we achieve this partially constrained HMM clustering (PC-HMM) by placing constraints on the expectation-maximization (EM) algorithm where a subset of parameters are used to cluster the repayments via the estimation process, while the other parameters are learned globally across all repayments. We compare our approach with three other baselines on a real-world loan repayment data set. We use an exogenous variable to validate and benchmark the clusters. We conclude our study with the observation that the ability to cluster on selective parameters, in conjunction with the structural construct of HMMs, enables the discovery of substantially more meaningful business insights than the baselines.<\/jats:p>","DOI":"10.1145\/3242734.3242741","type":"journal-article","created":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T11:58:04Z","timestamp":1532606284000},"page":"98-113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Improved Insights on Financial Health through Partially Constrained Hidden Markov Model Clustering on Loan Repayment Data"],"prefix":"10.1145","volume":"49","author":[{"given":"Dibu John","family":"Philip","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"}]},{"given":"Nandan","family":"Sudarsanam","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"}]},{"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"}]}],"member":"320","published-online":{"date-parts":[[2018,7,25]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2015.04.007"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1057\/9780230303829_5"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1108\/13581981211218289"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600851"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/1468-2427.00384"},{"key":"e_1_2_1_6_1","volume-title":"Behavior revealed in mobile phone usage predicts loan repayment. arXiv preprint arXiv:1712.05840","author":"Bj\u00f6rkegren D.","year":"2017","unstructured":"Bj\u00f6rkegren , D. , & Grissen , D. ( 2017 ). Behavior revealed in mobile phone usage predicts loan repayment. arXiv preprint arXiv:1712.05840 . Bj\u00f6rkegren, D., & Grissen, D. (2017). Behavior revealed in mobile phone usage predicts loan repayment. arXiv preprint arXiv:1712.05840."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1538-4616.2007.00092.x"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the Joint 9th IFSA World Congress and 20th NAFIPS International Conference, (pp. 2160--2164)","author":"Chen G.","year":"2001","unstructured":"Chen , G. , Wei , Q. , & Zhang , H. ( 2001 ). Discovering similar time-series patterns with fuzzy clustering and DTW methods . Proceedings of the Joint 9th IFSA World Congress and 20th NAFIPS International Conference, (pp. 2160--2164) . Vancouver, BC, Canada. Chen, G., Wei, Q., & Zhang, H. (2001). Discovering similar time-series patterns with fuzzy clustering and DTW methods. Proceedings of the Joint 9th IFSA World Congress and 20th NAFIPS International Conference, (pp. 2160--2164). Vancouver, BC, Canada."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2481674.2481683"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972726.12"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.2307\/1909582"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.2307\/2085979"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.05.030"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2014.12.041"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/41.8.578"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2007.09.013"},{"key":"e_1_2_1_17_1","volume-title":"Central Bank of Ireland.","author":"Gaffney E.","year":"2014","unstructured":"Gaffney , E. , Kelly , R. , & McCann , F. ( 2014 ). A transitions-based framework for estimating expected credit losses. Research Technical Paper 16RT14 , Central Bank of Ireland. Gaffney, E., Kelly, R., & McCann, F. (2014). A transitions-based framework for estimating expected credit losses. Research Technical Paper 16RT14, Central Bank of Ireland."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/14697680500039951"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1057\/9780230280830_23"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_2_1_21_1","volume-title":"Algorithms for clustering data","author":"Jain A. K.","year":"1988","unstructured":"Jain , A. K. , & Dubes , R. C. ( 1988 ). Algorithms for clustering data . Englewood Cliffs, NJ : Prentice Hall . Jain, A. K., & Dubes, R. C. (1988). Algorithms for clustering data. Englewood Cliffs, NJ: Prentice Hall."},{"key":"e_1_2_1_22_1","volume-title":"Exact indexing of dynamic time warping. Knowledge and information systems, 7(3), 358--386","author":"Keogh E.","year":"2005","unstructured":"Keogh , E. , & Ratanamahatana , C. A. ( 2005 ). Exact indexing of dynamic time warping. Knowledge and information systems, 7(3), 358--386 . Keogh, E., & Ratanamahatana, C. A. (2005). Exact indexing of dynamic time warping. Knowledge and information systems, 7(3), 358--386."},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the 26th Annual Conference of the Gesellschaft f\u00fcr Klassifikation, (pp. 561--569)","author":"Knab B.","year":"2002","unstructured":"Knab , B. , Schliep , A. , Steckemetz , B. , & Wichern , B. ( 2002 ). Model-based clustering with hidden Markov models and its application to financial time-series data . Proceedings of the 26th Annual Conference of the Gesellschaft f\u00fcr Klassifikation, (pp. 561--569) . University of Mannheim, Baden-W\u00fcrttemberg, Germany. Knab, B., Schliep, A., Steckemetz, B., & Wichern, B. (2002). Model-based clustering with hidden Markov models and its application to financial time-series data. Proceedings of the 26th Annual Conference of the Gesellschaft f\u00fcr Klassifikation, (pp. 561--569). University of Mannheim, Baden-W\u00fcrttemberg, Germany."},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the Conference on International Research on Food Security, Natural Resource Management and Rural Development, (pp.1--4)","author":"Kohansal M. R.","year":"2009","unstructured":"Kohansal , M. R. , & Mansoori , H. ( 2009 ). Factors affecting on loan repayment performance of farmers in Khorasan-Razavi province of Iran . Proceedings of the Conference on International Research on Food Security, Natural Resource Management and Rural Development, (pp.1--4) . University of Hamburg, Germany. Kohansal, M. R., & Mansoori, H. (2009). Factors affecting on loan repayment performance of farmers in Khorasan-Razavi province of Iran. Proceedings of the Conference on International Research on Food Security, Natural Resource Management and Rural Development, (pp.1--4). University of Hamburg, Germany."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jedc.2008.03.006"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(01)00228-X"},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning, (pp. 543--550)","author":"Li C.","year":"2000","unstructured":"Li , C. , & Biswas , G. ( 2000 ). A Bayesian approach to temporal data clustering using hidden Markov models . Proceedings of the Seventeenth International Conference on Machine Learning, (pp. 543--550) . Stanford, CA, USA. Li, C., & Biswas, G. (2000). A Bayesian approach to temporal data clustering using hidden Markov models. Proceedings of the Seventeenth International Conference on Machine Learning, (pp. 543--550). Stanford, CA, USA."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1057\/fsm.2009.28"},{"key":"e_1_2_1_29_1","volume-title":"Hidden Markov models in finance","author":"Mamon R. S.","year":"2007","unstructured":"Mamon , R. S. , & Elliott , R. J. (Eds.). ( 2007 ). Hidden Markov models in finance . New York : Springer . Mamon, R. S., & Elliott, R. J. (Eds.). (2007). Hidden Markov models in finance. New York: Springer."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2601922"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.09.024"},{"key":"e_1_2_1_32_1","volume-title":"Drop-outs among selected Zambian microfinance institutions: Causes and potential impact on product design. MicroSave-Africa Research Report","author":"Musona D.","year":"2001","unstructured":"Musona , D. , & Coetzee , G. ( 2001 ). Drop-outs among selected Zambian microfinance institutions: Causes and potential impact on product design. MicroSave-Africa Research Report , Nairobi . Musona, D., & Coetzee, G. (2001). Drop-outs among selected Zambian microfinance institutions: Causes and potential impact on product design. MicroSave-Africa Research Report, Nairobi."},{"key":"e_1_2_1_33_1","volume-title":"Proceedings of the IJCAI-99 workshop on neural, symbolic and reinforcement learning methods for sequence learning, (pp. 17--21)","author":"Oates T.","year":"1999","unstructured":"Oates , T. , Firoiu , L. , & Cohen , P. R. ( 1999 ). Clustering time series with hidden Markov models and dynamic time warping . Proceedings of the IJCAI-99 workshop on neural, symbolic and reinforcement learning methods for sequence learning, (pp. 17--21) . Stockholm, Sweden. Oates, T., Firoiu, L., & Cohen, P. R. (1999). Clustering time series with hidden Markov models and dynamic time warping. Proceedings of the IJCAI-99 workshop on neural, symbolic and reinforcement learning methods for sequence learning, (pp. 17--21). Stockholm, Sweden."},{"key":"e_1_2_1_34_1","volume-title":"Customer suitability in the retail sale of financial products and services.","author":"Basel Committee on Banking Supervision.","year":"2008","unstructured":"Basel Committee on Banking Supervision. ( 2008 ). Customer suitability in the retail sale of financial products and services. Retrieved from http:\/\/www.bis.org\/publ\/joint20.pdf. {Online; accessed 7-February-2017}. Basel Committee on Banking Supervision. (2008). Customer suitability in the retail sale of financial products and services. Retrieved from http:\/\/www.bis.org\/publ\/joint20.pdf. {Online; accessed 7-February-2017}."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/645890.671272"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1086\/452613"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/00220388.2013.775421"},{"key":"e_1_2_1_39_1","volume-title":"Repayment performance in group-based credit programs in Bangladesh: An empirical analysis. World development, 25(10), 1731--1742","author":"Sharma M.","year":"1997","unstructured":"Sharma , M. , & Zeller , M. ( 1997 ). Repayment performance in group-based credit programs in Bangladesh: An empirical analysis. World development, 25(10), 1731--1742 . Sharma, M., & Zeller, M. (1997). Repayment performance in group-based credit programs in Bangladesh: An empirical analysis. World development, 25(10), 1731--1742."},{"key":"e_1_2_1_40_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems, (pp. 648--654)","author":"Smyth P.","year":"1997","unstructured":"Smyth , P. ( 1997 ). Clustering sequences with hidden Markov models . Proceedings of the Advances in Neural Information Processing Systems, (pp. 648--654) . Denver, CO, USA. Smyth, P. (1997). Clustering sequences with hidden Markov models. Proceedings of the Advances in Neural Information Processing Systems, (pp. 648--654). Denver, CO, USA."},{"key":"e_1_2_1_41_1","volume-title":"Mumbai, India.","author":"Sudarsanam N.","year":"2016","unstructured":"Sudarsanam , N. , & Philip , D. J. ( 2016 ). Quantifying and predicting prepayments in the microfinance environment. Paper presented at the NSE-IFMR Finance Foundation Financial Deepening and Household Finance Research Initiative Conference , Mumbai, India. Sudarsanam, N., & Philip, D. J. (2016). Quantifying and predicting prepayments in the microfinance environment. Paper presented at the NSE-IFMR Finance Foundation Financial Deepening and Household Finance Research Initiative Conference, Mumbai, India."},{"key":"e_1_2_1_42_1","volume-title":"Volos, Greece.","author":"Tsinaslanidis P.","year":"2014","unstructured":"Tsinaslanidis , P. , Alexandridis , A. , Zapranis , A. , & Livanis , E. ( 2014 ). Dynamic time warping as a similarity measure: Applications in finance. Paper presented at the conference of the Hellenic Finance and Accounting Association , Volos, Greece. Tsinaslanidis, P., Alexandridis, A., Zapranis, A., & Livanis, E. (2014). Dynamic time warping as a similarity measure: Applications in finance. Paper presented at the conference of the Hellenic Finance and Accounting Association, Volos, Greece."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/1540-6229.00356"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.worlddev.2003.09.004"},{"key":"e_1_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Wang G.-J. Xie C. Han F. & Sun B. (2012). Similarity measure and topology evolution of foreign ex-change markets using dynamic time warping method: Evidence from minimal spanning tree. Physica A: Statistical Mechanics and its Applications 391(16) 4136--4146.  Wang G.-J. Xie C. Han F. & Sun B. (2012). Similarity measure and topology evolution of foreign ex-change markets using dynamic time warping method: Evidence from minimal spanning tree. Physica A: Statistical Mechanics and its Applications 391(16) 4136--4146.","DOI":"10.1016\/j.physa.2012.03.036"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.12.020"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2005.07.007"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/1540-6229.00477"}],"container-title":["ACM SIGMIS Database: the DATABASE for Advances in Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242734.3242741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3242734.3242741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:57:22Z","timestamp":1750208242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242734.3242741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,25]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,7,25]]}},"alternative-id":["10.1145\/3242734.3242741"],"URL":"https:\/\/doi.org\/10.1145\/3242734.3242741","relation":{},"ISSN":["0095-0033","1532-0936"],"issn-type":[{"type":"print","value":"0095-0033"},{"type":"electronic","value":"1532-0936"}],"subject":[],"published":{"date-parts":[[2018,7,25]]},"assertion":[{"value":"2018-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}