Paper Title
Intelligent Financial Early Warning System for SMEs: An Implementation in Energy Industry

Small and medium-sized enterprises (SMEs) play a very important role in Turkish economy owing to their large share in total number of enterprises and in total employment. Small and Medium-Sized Enterprises (SMEs) constituted 99.8% of total number of enterprises, 73.5% of employment, 54.1% of wages and salaries, 62% of turnover, 53.5% of value added at factor cost and 55% of gross investment in tangible goods in Turkey. But, they have some weaknesses such as low level usage of bank credits, insufficient access to finance, insufficient credit guarantee system, lack of capital for new and high technology investments, R&D and innovation and insufficient education level on finance. In these conditions SMEs should be aware of their own status, of when and where they should take necessary actions in response to their financial problems, as soon as possible rather than when the problems are beyond their control and reach a crisis. Therefore, to bring out the financial distress risk factors into open as early warning signals have a vital importance for SMEs as all enterprises. Theaim of thisstudy is topresent a model andintroduce a softwareforSMEstobring out the financial risk factors into open as early warning signals and to present this model in the energy industry. The energy industry will be the main parameter that determines growth and welfare both in our country and in the world. Therefore, the energy industry was selected for the implementation.Study is covereddata of SMEs in during 1988- 2013. Data of firmswasobtainedfromTurkish Central Bank (TCB) afterpermission. Total number of firms had financialdatawereover 250.000 in TCB duringthisperiod. Financial data that are gained from balance sheets and income statements was used to calculate financial ratios as variablesfor data mining. In this study, Chi-Square Automatic Interaction Detector (CHAID) which is one of the most efficient and up-to-date data mining methods in decision tree algorithms is used for detecting early warning signals. This study is the biggest study as covered amount and also first study that designed an intelligent data mining model with R integration for SMEs in Turkey. This study is a project funded by The Small and Medium Enterprises Development Organization. Keywords - Financial Early Warning System, Data Mining, Business Intelligence, R integration, Energy Industry.