Open Access Open Access  Restricted Access Subscription or Fee Access

Machine learning-based FEMA Transitional Shelter Assistance (TSA) eligibility prediction models

Mahdi Afkhamiaghda, Emad Elwakil, PhD, PE, CCE, PMP


Around 90 percent of the natural disasters in the United States involve floods. As a result of these floods, a massive number of houses become uninhabitable for their residents, making them in immediate need of lodging and shelters. The Federal Emergency Management Agency (FEMA) lodges people in noncongregated shelters such as hotels/motels for a short period—up to 45 days—through the Transitional Shelter Assistance (TSA) program. Government Accountability Office estimated that between 600 million and 1.4 billion dollars had been improperly spent. However, currently, the process of how an applicant becomes eligible for the TSA lacks a robust model and framework. However, the mechanism of selecting the recipients of TSA is mainly based on expert opinion and tacit knowledge. The objectives of this paper are (1) investigating how classification techniques can be used to help FEMA decision-makers during the time of the disaster and (2) building supervised machine learning decision-making models based on logistic regression, decision tree, and K nearest neighbor classification techniques using Python. The 4.8 million registries of applications dataset used for this paper were extracted from the National Emergency Management Information System. This research will help FEMA decision-makers for predicting TSA eligibility.


classification technique, data-driven decision-making, machine learning

Full Text:



Roser M, Ritchie H, Ortiz-Ospina E, et al.: Coronavirus disease (COVID-19)—Statistics and research. Our World in data. 2020. Available at Accessed February 8, 2020.

Wright RE: Flood Insurance Reform: FEMA’s Perspective. Washington, DC: FEMA, 2017.

Hong Y: A study on the condition of temporary housing following disasters: Focus on container housing. Front Architect Res. 2017; 6(3): 374-383. DOI:10.1016/J.FOAR.2017.04.005.

Abulnour AH: The post-disaster temporary dwelling: Fundamentals of provision, design and construction. HBRC J. 2014; 10(1): 10-24. DOI:10.1016/j.hbrcj.2013.06.001.

Félix D, Branco JM, Feio A: Temporary housing after disasters: A state of the art survey. Habitat Int. 2013; 40: 136-141. DOI:10.1016/J.HABITATINT.2013.03.006.

FEMA: Transitional shelter assistance fact sheet. 2017. Available at Accessed April 14, 2020.

FEMA: Transitional sheltering assistance. 2020. Available at Accessed May 21, 2020.

Hayles CS: An examination of decision making in post disaster housing reconstruction. Int J Disaster Resil Built Environ. 2010: 377-385.

Banholzer S, Kossin J, Donner S: The impact of climate change on natural disasters. In Reducing Disaster: Early Warning Systems for Climate Change. Dordrecht: Springer. 2014: 21-49. DOI:10.1007/978-94-017-8598-3_2.

Platt S, Brown D, Hughes M: Measuring resilience and recovery. Int J Disaster Risk Reduct. 2016; 19: 447-460. DOI:10.1016/J.IJDRR.2016.05.006.

Afkhamiaghda M, Afsari K, Elwakil E, et al.: An approach to simulating construction process in post-disaster sheltering. In 55th Annual ASC International Conference 2019. Denver, CO, 2019.

Susman P, O’Keefe P, Wisner B: Interpretations of clamity. In Hewitt K (ed.): Interpretations of Clamity; from the Viewpoint of Human Ecology. New York, NY: Routledge, 2019: 263-280.

Kutz GD, Ryan Hurricanes Katrina and Rita disaster relief: Prevention is the key to minimizing fraud, waste, and abuse in recovery efforts, statement of Gregory Kutz, Managing Director Forensic Audits and Special Investigations, Testimony before the Committee on Homeland Security and Governmental Affairs, US Senate. United States Government Accountability Office, no. GAO-07-418T. United States Government Accountability Office, 2007.

Ouyang M, Fang Y: A mathematical framework to optimize critical infrastructure resilience against intentional attacks. Comput-Aided Civ Infrastruct Eng. 2017; 32(11): 909-929.

Panakkat A, Adeli H: Neural network models for earthquake magnitude prediction using multiple seismicity indicators. Int J Neural Syst. 2007; 17(1): 13-33.

Galbusera L, Giannopoulos G, Argyroudis S, et al.: A Boolean networks approach to modeling and resilience analysis of interdependent critical infrastructures. Comput-Aided Civ Infrastruct Eng. 2018; 33(12): 1041-1055.

Kousky C, Michel-Kerjan EO, Raschky PA: Does federal disaster assistance crowd out flood insurance? J Environ Econ Manag. 2018; 87: 150-164. DOI:10.1016/j.jeem.2017.05.010.

FEMA: Understanding individual assistance and public assistance. 2017. Available at Accessed May 21, 2020.

Kousky C, Michel-Kerjan EO, Raschky PA: Does federal disaster assistance crowd out flood insurance? J Environ Econ Manag. 2018; 87: 150-164. DOI:10.1016/j.jeem.2017.05.010.

Dev KN, Das AK: Sheltering emergencies: Design development process of temporary housing in post-disaster settlement by community participation. In DS 101: Proceedings of NordDesign 2020, Lyngby, Denmark, 12-14 August 2020, 2020: 1-10.

Alshawawreh L, Pomponi F, D’Amico B, et al.: Qualifying the sustainability of novel designs and existing solutions for post-disaster and post-conflict sheltering. Sustainability. 2020; 12(3): 890.

Jahangiri K, Borgheipour H, Gendeshmin SB, et al.: Site selection criteria for temporary sheltering in urban environment. Int J Disaster Resil Built Environ. 2019; 11(1): 58-70.

Asfour OS: Learning from the past: Temporary housing criteria in conflict areas with reference to thermal comfort. Int J Disaster Risk Reduct. 2019; 38: 101206.

Pomponi F, Moghayedi A, Alshawawreh L, et al.: Sustainability of post-disaster and post-conflict sheltering in Africa: What matters? Sustain Prod Consump. 2019; 20: 140-150.

McCorduck P, Cfe C: Machines Who Think: A Personal Inquiry Into the History and Prospects of Artificial Intelligence. Boca Raton, FL: CRC Press, 2004. Available at Accessed February 19, 2020.

Marr B: How much data do we create every day? The mind-blowing stats everyone should read. 2018. Available at Accessed February 19, 2020.

Panch T, Szolovits P, Atun R: Artificial intelligence, machine learning and health system. Global Health. 2018; 8(2): 3-6.

Press G: 120 AI predictions for 2020. 2019. Available at Accessed February 19, 2020.

Bini SA: Artificial intelligence, machine learning, deep learning, and cognitive computing: What do these terms mean and how will they impact health care? J Arthroplast. 2018; 33(8): 2358-2361.

Beam AL, Kohane IS: Big data and machine learning in health care. JAMA. 2018; 319(13): 1317-1318.

Alvanchi A, Seyrfar A: Improving facility management of public hospitals in Iran using building information modeling. Sci Iran. 2020; 27(6): 2817-2829.

Tixier AJP, Hallowell MR, Rajagopalan B, et al.: Application of machine learning to construction injury prediction. Automat Construct. 2016; 69: 102-114.

Mohri M, Rostamizadeh A, Talwalkar A: Foundations of machine learning. 2018. Available at Accessed February 23, 2020.

Ghahramani Z, Jordan IM: Supervised learning from incomplete data via an em approach. In Advances in Neural Information Processing Systems. Uma Ética Para Quantos? 2012; XXXIII(2): 81-87. DOI:10.1007/s13398-014-0173-7.2.

Hastie T, Tibshirani R, Friedman J: Unsupervised learning. In The Elements of Statistical Learning. 2nd ed., vol. 27. 2009: 485-493. DOI:10.1007/b94608.

Long WJ, Griffith JL, Selker HP, et al.: A comparison of logistic regression to decision-tree induction in a medical domain 1 introduction 2 methodology. Computer and Biomedical Research. 1993; 26(1): 74-97.

Shaikhina T, Lowe D, Daga S, et al.: Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation. Biomed Sig Process Control. 2019; 52: 456-462. DOI:10.1016/j.bspc.2017.01.012.

Tso GKF, Yau KKW: Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks. Energy. 2007; 32(9): 1762-2768.

Liu L: Heart Failure: Epidemiology and Research Methods. Amsterdam: Elsevier, 2018.

Kleinbaum DG, Klein M: Logistic regression: A self-learning text. In Gail M, Krickeberg K, Samet JM, Tsiatis A, Wong W (eds.): Berlin: Springer. The Quarterly Review of Biology, 3rd ed., vol. 84. 2010. DOI:10.1086/648138.

Hoffman JI: Basic Biostatistics for Medical and Biomedical Practitioners, 2nd ed. Amsterdam: Elsevier, 2019.

Brownlee J: K-nearest neighbors for machine learning. Machine Learning Mastery 2016; 15.

Keller JM, Gray MR, Givens JA: A fuzzy k-nearest neighbor algorithm. IEEE Trans Syst Man Cybernet. 1985; 4: 580-585.

Prasath VBS, Alfeilat HAA, Hassanat ABA, et al.: Distance and similarity measures effect on the performance of K-nearest neighbor classifier—a review. Big Data. 2017; 1–39. DOI:10.1089/big.2018.0175.

Chen HL, Yang B, Wang G, et al.: A novel bankruptcy prediction model based on an adaptive fuzzy k-nearest neighbor method. Knowl Based Syst. 2011; 24(8): 1348-1359. DOI:10.1016/j.knosys.2011.06.008.

Visa S, Ramsay B, Ralescu A, et al.: Confusion matrix-based feature selection. In Proceedings of the Twenty-Second Midwest Artificial Intelligence and Cognitive Science Conference. Cincinnati, OH: University of Cincinnati, 2011: 120-227.

FEMA: Open FEMA dataset: Individual assistance housing registrants large disasters-V1. 2019. Available at Accessed May 5, 2020.

Corchado E, Yin H: In Corchado E, Yin H (eds.): Intelligent Data Engineering and Automated Learning-IDEAL 2009. In 10th International Conference, Burgos, Spain, September, 2009; 23-26.

Iglewicz B, Hoaglin D: How to detect and handle outliers. In Mykyta EF (ed.): The ASQC Basic References in Quality Control: Statistical Techniques. 1993; 16: 1-87.

Norman GR, Streiner D: Biostatistics the Bare Essentials, 3rd ed. Shelton, CT: People’s Medical Publishing House, 2008.

Kenton W: Overfitting. 2019. Available at

Vabalas A, Gowen E, Poliakoff E, et al.: Machine learning algorithm validation with a limited sample size. PLoS One. 2019; 14(11): e0224365.

Wilson AJC: The probability distribution of X-ray intensities. Acta Crystallogr. 1949; 2(5): 318-321.

Dai B, Ding S, Wahba G: Multivariate Bernoulli distribution. Bernoulli. 2013; 19(4): 1465-1483.

Monroe W: Bernoulli and binomial random variables. 2017. Available at

Kelley D: Introduction to Probability. London: Macmillan Publishing Company, 1994.

Everitt BS, Skrondal A: The Cambridge Dictionary of Statistics. Cambridge, MA: Cambridge University Press, 2010.

Lam KC, Palaneeswaran E, Yu CY: A support vector machine model for contractor prequalification. Autom Construct. 2009; 18(3): 321-329.

Cheng MY, Peng HS, Wu YW, et al.: Estimate at completion for construction projects using evolutionary support vector machine inference model. Autom Construct. 2010; 19(5): 619-629.

Soibelman L, Kim H: Data preparation process for construction knowledge generation through knowledge discovery in databases. J Comput Civil Eng. 2002; 16(1): 39-48.



  • There are currently no refbacks.

Copyright (c) 2021 Journal of Emergency Management