<![CDATA[The classification technique and data forecasting will probably be one of the techniques that will often be needed in handling or managing big data. So, from that the author analyzes the possible development of the existing algorithms. The purpose is to find possibilities in the use of reliable algorithms in a particular field, then can be adopted and implemented to develop forecasting techniques in the future. Based on these considerations, the authors conducted experiments by applying LVQNN to conduct shortterm forecasting on daily period of the Rupiah exchange rate. The literature that is used as a reference is the discovery of architectural data classification processes that resemble forecasting techniques. So, when there is a combination of Rupiah exchange histories, it is possible to find these combinations into certain classes based on predetermined parameters and historical data combination data and forecast values in the past. In this research the factors chosen as indicators that affect the Rupiah exchange rate are the amount of exports, the amount of imports, the inflation rate and also the world oil price. In this research the highest accuracy value in the testing process for the population reached 99.0991%. The increase in the percentage value of forecasting accuracy is influenced by the composition of the data. In this study the formation of data composition is influenced by distinct data. The selection of parameters which become distinct claused determines how the composition of the data will be formed. If the composition of the data is not correct, the test results will not be good. If the number of weights vector is smaller than the input data, the forecasting accuracy will decrease. Because the weight vector cannot represent data combinations that used during training or testing.]]>
