A Conunercial Bank is a financial intermediary that holds deposits for individuals andrnbusinesses in the form of checking and savings accounts and certificates of deposit of varyingrnmaturities while it issues loans in the form of personal and business as well as mortgages. Itrnarises due to a debtor's non-payment of a loan or other line of credit.rnIn order to control and manage the risk, banks normally have discipline called riskrnmanagement. Hence it is very important to develop and implement an effective technologyrnthat can support risk management. This research focused on the application of data miningrntechniques in supporting loan risk assessment taking as case study United Bank SharernCompany. It used two data mining techniques namely, decision tree and neural network.rnDifferent decision tree models using j48 algorithm were constructed during the experimentsrnand among them a tree with overall accuracy of 95 .65% with conceivable rule was selected.rnThe important attributes that were identified by the selected decision tree were: Networkingrncapital, Current Ratio, Total Asset, TLfA, Current Liability, Collateral Value, Years inrnBusiness, Number of prior term loans settled, Performance of term Preordains, CollateralrnType, Credit Relationship with other bank, Trade Sector, Performance in other types of loanrnand Current Asset.rnBased on the above selected attributes different types of neural network models withrnmultilayer perception algorithm were constructed and a model that maximizes the accuracy inrnpredicting poor payment performance was selected with over all accuracy of 92.83%.rnWhen evaluation was done, the overall accuracy of decision tree found better than the neuralrnnetwork even if nether research is needed in addition the result of decision tree is morerninterpret able than neural network. In general the result showed the possible application of datarnmining in loan risk assessment term joan.