Long Short Term Memory (LSTM) is known as optimized Recurrent Neural Network (RNN) architectures that overcome RNN’s lact about maintaining long period of memories. As part of machine learning networks, LSTM also notable as the right choice for time-series prediction. Currently, machine learning is a burning issue in economic world, abundant studies such predicting macroeconomic and microeconomics indicators are emerge. Inflation rate has been used for decision making for central banks also private sector. In Indonesia, CPI (Consumer Price Index) is one of best practice inflation indicators besides Wholesale Price Index and The Gross Domestic Product (GDP). Since CPI data could be used as a direction for next inflation move, we conducted CPI prediction model using LSTM method. The network model input consists of 28 variables of staple price in Surabaya and the output is CPI value, also the entire development of prediction model are done in Amazon Web Service (AWS) Cloud. In the interest of accuracy improvement, we used several optimization algorithm i.e. Stochastic Gradient Descent (sgd), Root Mean Square Propagation (RMSProp), Adaptive Gradient(AdaGrad), Adaptive moment (Adam), Adadelta, Nesterov Adam (Nadam) and Adamax. The results indicate that Nadam has 4,008 RMSE’s value, less than other algorithm which indicate the most accurate optimization algorithm to predict CPI value.

Prediction technique is one of the areas in data mining where it finds patterns from a set of data lead to predictions in the future. Prediction in the economic field is a predominant prediction due to one of the parameters for the country development. The Consumer Price Index describes the level of consumption of goods and services in society that used as a reference for the inflation rate. Previously the majority of research that predicts the Consumer Index value only predicts the value of the Consumer Price Index itself as an input and output value. The study built a forecasting model by utilizing multi input variables, namely 28 types of daily staple food prices as input values to predict Consumer Price Index of Surabaya for the period 2014 to 2018 where the whole development predictions built the Amazon Cloud Services environment. The prediction system is built using Multilayer Perceptron algorithm with architectural variations of the number of neurons, epoch, and hidden layer. Based on the test results, the best accuracy with RMSE value 3,380 is generated by 2 hidden layers, the first and second hidden layers which have 10 of neurons respectively with 1000 epoch.

Multivariate Time Series based forecasting is a type of forecasting that has more than one criterion changes from time to time that it can forecast based on historical patterns of data sequences. The Consumer Price Index (CPI) issued regularly every month by the Statistics Indonesia calculated based on data observations. This study is a development of previous research that only used on type of algorithm to predict CPI value resulting poor of accuracy due to lack of architecture variations testing. This study developed a CPI forecasting model with a new approach about using several types of deep learning algorithms, namely LSTM, Bidirectional LSTM, and Multilayer Perceptron with architectural variations of the number of neurons and epochs. Furthermore, this study adapt ADDIE model of Research and Development method. Based on the results, the best accuracy is obtained from the LSTM Bidirectional with 10 neurons and 2000 epoch resulting 3,519 of RMSE value. Meanwhile, based on the average RMSE value for the whole test, LSTM gets the smallest average of RMSE followed Bidirectional LSTM and Multilayer Perceptron with the RMSE value 4,334, 5,630, 6,304 respectively.

Long Short Term Memory (LSTM) is known as optimized Recurrent Neural Network (RNN) architectures that overcome the lack of RNN’s about maintaining long period of memories information. As part of machine learning networks, LSTM also notable as the right choice for time-series prediction. Inflation rate has been used for decision making for central banks also private sector. In Indonesia, CPI (Consumer Price Index) is one of best practice inflation indicators besides Wholesale Price Index and The Gross Domestic Product (GDP). Since CPI data could be used as a direction for next inflation move, we conducted CPI prediction model using Long Short Term Memory Method. The network model input consists of 34 variables of staple price in Surabaya and the output is CPI value. In the interest of predictive accuracy improvement, we used several optimization algorithm i.e. Stochastic Gradient Descent (sgd), Root Mean Square Propagation (RMSProp), Adaptive Gradient (AdaGrad), Adaptive moment (Adam), Adadelta, Nesterov Adam (Nadam) and Adamax. The result indicate that Nesterov Adam has 4.088 RMSE’s value, less than other algorithm which indicate the most accurate optimization algorithm to predict CPI value.

No abstract