Forecasting Macroeconomic Parameters with Deep Learning Neural Networks

Project Meeting (17/11/2017) Topics Discussed Report Structure Intro Lit Review Financial time series - description/properties preprocessing modelling - arima models AI models Lagramge Mathew Butler ’s paper Neural Networks for modelling time series (this should be half of the lit review) general NN … Problem Analysis Research Hypothesis - mention using arima as baseline Software Engineering Requirements Gantt chart Ethics Statement? Design and implementation - ARIMA experiments Results and Evaluation Put results from ARIMA experiments here Appendix - all results go here Writing workflow Writing things up should ideally happen after immediately after performing experiment. Experiments generally should not be repeated until project is pretty much done. while report not finished Perform Experiment Write Results and Evaluation Write Design and Implementation Write Problem Analysis Write Literature Review Tasks Comp...

Topics Discussed Experiments performed Discussed the experiment results and how to interpret them. Even if overall forecast is not very accurate, determining the direction in which the variable will go is still valuable. Should produce a plot (3D / heatmap) of hyper-parameter grid search. Results from this paper Useful to see “recursive” prediction results to compare with the ones obtained with neural networks. A prediction of two years ahead is very good. Maybe possible to motivate use of deep learning for forecasting based on results from non-linear equation discovery models. Further experiments Should create an ARIMA and use it as a benchmark to compare results from neural nets. Further univariate variable experiments should be performed using seasonal and trend decomposition on input data and first order difference. Tasks Competed [x] Perform experiments with simple NN. [x] Establish experimentation workflow. Tasks for Next Week [] Create b...

Topics Discussed Software Engineering Aspect of Project Need to have software engineering aspect of project. Potential ideas to be explored: Requirements engineering Unit Testing Planning - Gant Chart Report Structure Potential page limits for individual sections were discussed: Introduction: 2 Lit Review: 10 Problem Analysis: 5 Design and Implementation: 10 Results and Evaluation: 10 Conclusion: 3 Neural Network Initial experiments with a simple architecture need to be conducted. Experimentation workflow should be established in order to enable fast reliable prototyping. Unit tests can be used to ensure reliability of experiments. Statistical tests will be used to compare the performance of different architectures (ANOVA).  Tasks Completed Learn about stationarity, trends and seasonality. Analyse data - perform simple regression, figure out if it's stationary or not, identify trends and seasonality. Write up analysis. Read  Using R for Tim...

Topics Discussed Data Variables Meaning of variables in the data set CPI: Consumer price index. GDP: Gross domestic product UR: unemploymeent rate. IR Policy Rate - Interest rate (Possibly inflation subtracted from  nominal interest rate) LR10: Possibly 10 year loan rate. LR10 - IR: IR subtracted from LR10. Exrate Euro for 1 USD - exchange rate b/w euro and dollar. Wheather or not data has been preprocessed in any way - about to find out. Data analysis and preprocessing Should check if data is stationary or not. Identify any trend and seasonality. Test significance of each variable using a benchmark architecture (simple MLP). Explore different preprocessing techniques and if they improve performance on benchmark architecture. Longer term question - do we need more data?  Report Possible structure of Problem Analysis? Data - what kind and where froerform m? Stationarity, Seasonality, Trend Neural network architecture Tasks Completed Rea...

Topics discussed Literature Review Basic Structure (for now) Macroeconomics Importance of macroeconomic forecasting. Analysis of the data set and different parameters. Time Series Analysis of standard forecasting approaches. Discussion on seasonality, stationarity and other characteristics of time series data. Deep Learning Discussion of the emerging field of deep learning - advantages and disadvantages. Analysis of deep learning approaches. Macroeconomic Forecasting using Deep Learning Connecting the above topics and analysis on the work done in the field so far. Missing Data Dealing with missing values of parameters in the data should be done with caution. Possible solutions include leaving out data points with missing values or imputation techniques to estimate missing values. Leaving out data points may cause disruption in the continuity ofe the time series. Reading Resources Using R for Time Series Analysis  - Classical methods for time series analysis a...

Work done for past week Created project report outline in Latex. Created private GitHub repository for project. Started exploring Keras. Created reading list . The list includes all papers, books and past projects that I have read so far and will be continuously updated. Tasks for next week Read more on deep learning. Find research papers on: financial forecasting, time series prediction, deep learning, macroeconomic forecasting. Gain experience with Keras. Figure out correct formatting for project report (fonts, margins etc.) and modify document accordingly. Reading List Report Outline

Outcomes Discussed some reading resources. Established which data set is going to be used. Discussed means of communication - through blog. Discussed some past projects and context of the current project. Scheduled next meeting to discuss project structure. Tasks Create Blog Read past projects connected to macroeconomic forecasting and/or deep learning  Read paper from project description Familiarise myself with the data Start using Keras