Algeria's CPI Inflation Forecast Using DNN Methods

 Data Analysis | Data Science |Python | Tensorflow | Keras | Streamlit | Numpy | Pandas.

Problem Statement 

The accurate forecasting of Consumer Price Index (CPI) inflation is a crucial aspect of economic planning and decision-making. In the context of Algeria, where economic stability and development are paramount, the need for precise inflation predictions becomes even more pronounced. Traditional forecasting methods such as ARIMA may not fully capture the intricate patterns and dynamics inherent in inflation time series data. Therefore, there is a compelling need to explore and leverage advanced deep learning models, such as Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN), to enhance the accuracy and reliability of CPI inflation forecasts.

Project Objectives

Exploratory Data Analysis (EDA):

Train DNN Models:

    Interactive Forecasting Application:

Significance

This project's significance lies in its potential to influence economic decision-making, empower businesses and investors, enhance public awareness, contribute to technological advancements, and further academic research in the field of economic forecasting. By bridging the gap between advanced machine learning techniques and economic indicators, the project aligns with the broader goal of fostering economic resilience and sustainability.

Data

We begin with the unadjusted Algerian consumer price index (CPI), in the period January 2000 to December 2022. The series was gathered from IFS-IMF. We transform the adjusted series to a monthly year-on-year consumer price inflation rate.