Use of Machine Learning Algorithms: Accessing World Bank Database & Google Trends to Predict Economic Cycle - Statswork
In Brief:
- With the combination of math, statistics, and computer science, big data analysis and ML algorithms are becoming more and more computationally emphasized.
- Google Trends data can aid in advance in forecasts of the current level of activity for several different economic time series.
Google Trend is presently one of the most common analytics tools noted by numerous studies and applying by policymaker units. There are many details behind such as timeliness, a broad range of relevant study fields, user interface, and free data access.
Encouraged by advances in computing power, ML methods have recently been anticipated as substitutes to time-series regression models typically used by World banks for predicting main economic variables. The ML models are particularly suitable for handling large datasets when the number of possible regressions is more significant than that of existing explanations.
Conclusion
The enormous challenge to relate the advanced computational method, called ML algorithms for forecasting the big data in economic variables are totally different from traditionally parametric valuations and is more powerful. The ML systems can detect a vast amount of enlightening details in databases, including qualitative data, quantitative data, and time-series trends. With the minimization of modeling expectations, ML systems can proficiently compute both stationary and non-stationary data
Reference:
- Nowcasting Prices Using Google Trends An Application to Central America , 2015,Skipper Seabold , Andrea Coppola
- Predicting Recessions in Real-Time: Mining Google Trends and Electronic Payments Data for Clues, 2016, Greg Tkacz
- Quantifying macroeconomic expectations in stock markets using Google Trends , 2018, Johannes Bock
- An Algorithmic Crystal Ball: Forecasts-based on Machine Learning, 2018, Jin-Kyu Jung, Manasa Patnam, and Anna Ter-Martirosyan
Comments
Post a Comment