INFLATION PREDICTION WITH EXTERNAL FACTORS USING TIME SERIES MODELS AND DEEP LEARNING
Inflation is an important economic indicator that affects the economic stability of a country. Inflation is defined as a generalized and sustained increase in the prices of goods and services in an economy over a period of time. A proper understanding of inflation is necessary for effective decis...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/83444 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Inflation is an important economic indicator that affects the economic stability of a
country. Inflation is defined as a generalized and sustained increase in the prices of
goods and services in an economy over a period of time. A proper understanding of
inflation is necessary for effective decision and policy making. This final project
aims to develop a method to predict the inflation rate in Indonesia with a deep
learning approach, namely the Long Short-Term Memory (LSTM) model. For
comparison, Autoregressive Integrated Moving Average (ARIMA), Seasonal
Autoregressive Integrated Moving Average (SARIMA), and hybrid LSTMARIMA
and LSTM-SARIMA models are used. The hybrid model combines the
advantages of both approaches to improve prediction accuracy. In addition, a
comparison of the results when integrating external factors that are relevant to the
inflation rate will also be examined. In this final project, it is concluded that the
LSTM method with the integration of external factors produces the best
performance with a MAPE value of 8.47%. |
|---|