Ethiopian Airlines is a profit-oriented business organization whose objective is to providernthe maximum value to its customers, consistent with the need to make some return on eachrntransaction. One of the major primary activity at the airline is Sales. In addition, becauserncommercial organizations only survive by identifying and satisfying the market, MarketingrnServices is also regarded as a major primary activityrnThis study focuses on the revenue process within the Sales and Marketing operation. Inrnparticular, it aims at understanding the critical business functions and processes involvedrnin the flight revenue process, to identify and assess the availability of revenue datarnelements and develop a model for Ethiopian Airlines that will support information onrnrevenue realized by flight and forecast revenue by flight; accurately and timely.rnEthiopian Airlines has numerous state-of-the-art application systems and as a result retainsrna vast amount of data in its different databases. However, it has failed to make good use ofrnthis data and has not been able to use it to create competitive advantage. As a result, thernrevenue information model has been developed USll1g data mining techniques. Inrnpm1icular, the neural network model was used to train, test, validate and develop thernprototype model. The ultimate objective being to find out the suitability of data miningrnapplications to the Ethiopian Airlines problem. Since the scope of the study is limited to a single organization, the major method that hasrnbeen used to assess revenue information needs of users is case study; implementedrnthrough interviews (planned discussion), questionnaires, observation and documentrnanalysis.rnAfter reviewing the various areas that are affected by the Sales and Marketing operation;rnSales, Scheduling, Pricing, Revenue Management and Airport Operations have beenrnidentified as the critical functions in the revenue process. As a result the focus of the studyrnhas been on these functions.rnSurvey results reveal that of the 5 most important inforn1ation required by the concernedrnairline managers, revenue related information ranks on top with 31 % of respondentsrnranking it first. In addition, 84% of respondents rate flight revenue information as eitherrnone of the most or the most critical information, 88% as either very or extremely strategic,rnand 94% as one that would provide opportunity to gain competitive advantage.rnThe major revenue related data elements identified during the study are advanced bookingrndata, post departure data, schedule data, and revenue data. These revenue related datarnelements are available within the existing system, but are scattered in the variousrnapplication systems. Over one year's historic advance booking data is available, over twornyears' post-departure data is available, and historical flight revenue data since April, 1997rnis available.rnrnAfter selecting a suitable software to build a revenue infol111ation model, the revenuernrelated data elements identified were collected for 8 fliFghts and a comprehensive testingrnwas conducted. The test included 6 different experiments using the back propagationrnnetwork and radial basis function neural network models, 3 different sets of independentrnvariables and a multitude of training parameters. The experiments produced 327 differentrnmodels which were compared and evaluated and finally one was selected to represent thernrevenue infol111ation model. The developed model, with an average of 33-37% error rate, isrnonly a preliminary or initial step towards, hopefully, more detailed work in this area.rnI am confident that through a selection of more fields and with more historical data, thernerror may be able to be reduced to users' requirement of 5-10%. It is, therefore, my beliefrnthat this research has some contribution to further research in this area. It has been able tornsuccessfully demonstrate that data mining applications can be an alternative approach tornbuild infol111ation systems; especially for complex problems having vast amount of datarnand high interaction among non linear variables. Others can pursue similar research usingrndifferent types of data mining applications, including other neural network models. I hopernthat some of the problems I encountered and the methodologies I used will help to shedrnlight and guide others undertaking similar studies.