|
|
|
|
| LEADER |
02121cas a2200325 a 4500 |
| 001 |
AALejournalIMF016283 |
| 008 |
230101c9999 xx r poo 0 0eng d |
| 020 |
|
|
|c 5.00 USD
|
| 020 |
|
|
|z 9781513531724
|
| 022 |
|
|
|a 1018-5941
|
| 040 |
|
|
|a BD-DhAAL
|c BD-DhAAL
|
| 100 |
1 |
|
|a Bolhuis, Marijn.
|
| 245 |
1 |
0 |
|a Deus ex Machina? :
|b A Framework for Macro Forecasting with Machine Learning /
|c Marijn Bolhuis, Brett Rayner.
|
| 264 |
|
1 |
|a Washington, D.C. :
|b International Monetary Fund,
|c 2020.
|
| 300 |
|
|
|a 1 online resource (25 pages)
|
| 490 |
1 |
|
|a IMF Working Papers
|
| 500 |
|
|
|a <strong>Off-Campus Access:</strong> No User ID or Password Required
|
| 500 |
|
|
|a <strong>On-Campus Access:</strong> No User ID or Password Required
|
| 506 |
|
|
|a Electronic access restricted to authorized BRAC University faculty, staff and students
|
| 520 |
3 |
|
|a We develop a framework to nowcast (and forecast) economic variables with machine learning techniques. We explain how machine learning methods can address common shortcomings of traditional OLS-based models and use several machine learning models to predict real output growth with lower forecast errors than traditional models. By combining multiple machine learning models into ensembles, we lower forecast errors even further. We also identify measures of variable importance to help improve the transparency of machine learning-based forecasts. Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models. The framework also better predicts economic volatility, suggesting that machine learning techniques could be an important part of the macro forecasting toolkit of many countries.
|
| 538 |
|
|
|a Mode of access: Internet
|
| 650 |
|
7 |
|a ML Method
|2 imf
|
| 650 |
|
7 |
|a ML Model
|2 imf
|
| 650 |
|
7 |
|a RF Algorithm
|2 imf
|
| 650 |
|
7 |
|a SVM Regression
|2 imf
|
| 650 |
|
7 |
|a WP
|2 imf
|
| 651 |
|
7 |
|a Turkey
|2 imf
|
| 700 |
1 |
|
|a Rayner, Brett.
|
| 830 |
|
0 |
|a IMF Working Papers; Working Paper ;
|v No. 2020/045
|
| 856 |
4 |
0 |
|z Full text available on IMF
|u http://elibrary.imf.org/view/journals/001/2020/045/001.2020.issue-045-en.xml
|z IMF e-Library
|