{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:18:33Z","timestamp":1773105513358,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>We forecast monthly Canadian real GDP growth using machine learning models trained on Official macroeconomic indicators and Google Trends (GT) data. Predictors are selected dynamically in each rolling window using PDC-SIS, with cross-validation-based tuning to support real-time forecasting and avoid data leakage. The evaluation is conducted on the latest-available (final-vintage) series and should be interpreted as a pseudo out-of-sample forecasting exercise rather than real-time vintage nowcasting. We evaluate GBM, XGBoost, LightGBM, CatBoost, and Random Forest against an ARIMA baseline. Official data deliver the strongest performance at short and medium horizons, while combining Official and GT data yields the clearest improvement at the longest horizon. With GT data alone, LightGBM is the only ML model maintaining positive out-of-sample R2 across all horizons. Diebold\u2013Mariano tests corroborate these patterns: LightGBM dominates other ML models under GT-only predictors, whereas with Official and combined data, the horizon-specific best models significantly outperform ARIMA, with smaller differences among leading tree-based methods.<\/jats:p>","DOI":"10.3390\/make8030066","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T13:27:18Z","timestamp":1773062838000},"page":"66","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Feature Selection for Canadian GDP Forecasting: Machine Learning with Google Trends and Official Data"],"prefix":"10.3390","volume":"8","author":[{"given":"Shafiullah","family":"Qureshi","sequence":"first","affiliation":[{"name":"Data Analytics, Ministry of Jobs, Economy, Trade, and Immigration, Edmonton, AB T5J 4G8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-1762","authenticated-orcid":false,"given":"Ba M.","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Economics, Carleton University, Ottawa, ON K1S 5B6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanny S.","family":"Demers","sequence":"additional","affiliation":[{"name":"Department of Economics, Carleton University, Ottawa, ON K1S 5B6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Najib","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Finance, College of Business Administration (CBA), Prince Sultan University, P.O. Box 66833, Riyadh 11586, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5723-2177","authenticated-orcid":false,"given":"Ateeq ur Rehman","family":"Irshad","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Sciences, College of Humanities and Sciences (CHS), Prince Sultan University, P.O. Box 66833, Riyadh 11586, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Predicting Initial Claims for Unemployment Benefits","volume":"1","author":"Choi","year":"2009","journal-title":"Google Inc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1111\/j.1475-4932.2012.00809.x","article-title":"Predicting the present with Google Trends","volume":"88","author":"Choi","year":"2012","journal-title":"Econ. Rec."},{"key":"ref_3","unstructured":"Tkacz, G. (2013). Predicting Recessions in Real-Time: Mining Google Trends and Electronic Payments Data for Clues. C.D. Howe Inst. Comment., 387, Available online: https:\/\/www.cdhowe.org\/wp-content\/uploads\/2024\/12\/Commentary_387_0-1.pdf."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.ijforecast.2018.08.001","article-title":"Google data in Bridge equation models for German GDP","volume":"35","author":"Knetsch","year":"2019","journal-title":"Int. J. Forecast."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1080\/07350015.2022.2116025","article-title":"When Are Google Data Useful to Nowcast GDP? An Approach via Preselection and Shrinkage","volume":"41","author":"Ferrara","year":"2023","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1111\/j.1467-9868.2008.00674.x","article-title":"Sure independence screening for ultrahigh dimensional feature space","volume":"70","author":"Fan","year":"2008","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1111\/caje.12618","article-title":"A large canadian database for macroeconomic analysis","volume":"55","author":"Leroux","year":"2022","journal-title":"Can. J. Econ. Can. D\u2019\u00e9conomique"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"117092","DOI":"10.1016\/j.eswa.2022.117092","article-title":"Knowledge discovery for course choice decision in massive open online courses using machine learning approaches","volume":"199","author":"Nilashi","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1007\/s40747-023-01175-4","article-title":"Smart cities: The role of internet of things and machine learning in realizing a data-centric smart environment","volume":"10","author":"Ullah","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Alfaiz, N.S., and Fati, S.M. (2022). Enhanced credit card fraud detection model using machine learning. Electronics, 11.","DOI":"10.3390\/electronics11040662"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ashfaq, T., Khalid, R., Yahaya, A.S., Aslam, S., Azar, A.T., Alsafari, S., and Hameed, I.A. (2022). A machine learning and blockchain based efficient fraud detection mechanism. Sensors, 22.","DOI":"10.3390\/s22197162"},{"key":"ref_12","unstructured":"Biau, O., and D\u2019Elia, A. (2025, November 28). Euro Area GDP Forecasting Using Large Survey Datasets: A Random Forest Approach. Available online: https:\/\/www.mdpi.com\/authors\/."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tiffin, A. (2016). Seeing in the Dark: A Machine-Learning Approach to Nowcasting in Lebanon, International Monetary Fund.","DOI":"10.5089\/9781513568089.001"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jung, J.K., Patnam, M., and Ter-Martirosyan, A. (2018). An Algorithmic Crystal Ball: Forecasts-Based on Machine Learning, International Monetary Fund.","DOI":"10.5089\/9781484380635.001"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fuleky, P. (2020). Macroeconomic Forecasting in the Era of Big Data: Theory and Practice, Springer.","DOI":"10.1007\/978-3-030-31150-6"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1080\/07350015.2019.1637745","article-title":"Forecasting Inflation in a data-rich environment: The benefits of machine learning methods","volume":"39","author":"Medeiros","year":"2021","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1016\/j.ijforecast.2021.05.005","article-title":"Macroeconomic data transformations matter","volume":"37","author":"Coulombe","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0169-2070(00)00063-7","article-title":"Neural network forecasting of Canadian GDP growth","volume":"17","author":"Tkacz","year":"2001","journal-title":"Int. J. Forecast."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s00181-017-1254-1","article-title":"A dynamic factor model for nowcasting Canadian GDP growth","volume":"53","author":"Chernis","year":"2017","journal-title":"Empir. Econ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1257\/pandp.20191069","article-title":"Ensemble methods for causal effects in panel data settings","volume":"109","author":"Athey","year":"2019","journal-title":"AEA Pap. Proc."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.ijforecast.2014.03.004","article-title":"Forecasting economic activity with targeted predictors","volume":"31","author":"Bulligan","year":"2015","journal-title":"Int. J. Forecast."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1080\/07350015.2021.1899933","article-title":"Machine learning time series regressions with an application to nowcasting","volume":"40","author":"Babii","year":"2022","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Beyhum, J., and Striaukas, J. (2024). Factor-Augmented Sparse MIDAS Regressions with an Application to Nowcasting, KU Leuven. Faculty of Economics and Business Discussion Paper Series; DPS 24.14.","DOI":"10.2139\/ssrn.5035402"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s10614-020-10083-5","article-title":"Nowcasting US GDP using tree-based ensemble models and dynamic factors","volume":"57","author":"Soybilgen","year":"2021","journal-title":"Comput. Econ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10182-024-00515-0","article-title":"Nowcasting GDP using machine learning methods","volume":"109","author":"Kant","year":"2025","journal-title":"Asta Adv. Stat. Anal."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1002\/for.3193","article-title":"Predictor Preselection for Mixed-Frequency Dynamic Factor Models: A Simulation Study with an Empirical Application to GDP Nowcasting","volume":"44","author":"Franjic","year":"2025","journal-title":"J. Forecast."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1007\/s10614-022-10312-z","article-title":"Comparing out-of-sample performance of machine learning methods to forecast US GDP growth","volume":"62","author":"Chu","year":"2023","journal-title":"Comput. Econ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1080\/07350015.2021.1895812","article-title":"Targeting predictors via partial distance correlation with applications to financial forecasting","volume":"40","author":"Yousuf","year":"2022","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.].","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_30","unstructured":"Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective, The MIT Press."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_32","unstructured":"Saitta, L. (1996). Experiments with a new boosting algorithm. Proceedings of the Thirteenth International Conference on Machine Learning (ICML 1996), Morgan Kaufmann Publishers."},{"key":"ref_33","first-page":"801","article-title":"Arcing classifier","volume":"26","author":"Breiman","year":"1998","journal-title":"Ann. Stat."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1111\/ecin.13049","article-title":"Obtaining consistent time series from Google Trends","volume":"60","author":"Eichenauer","year":"2022","journal-title":"Econ. Inq."},{"key":"ref_37","first-page":"2382","article-title":"Partial distance correlation with methods for dissimilarities","volume":"42","author":"Rizzo","year":"2014","journal-title":"Ann. Stat."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1002\/jae.2910","article-title":"How is machine learning useful for macroeconomic forecasting?","volume":"37","author":"Leroux","year":"2022","journal-title":"J. Appl. Econom."},{"key":"ref_39","first-page":"283","article-title":"Random forests for time series","volume":"21","author":"Goehry","year":"2023","journal-title":"Revstat-Stat. J."},{"key":"ref_40","unstructured":"Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2017). CatBoost: Unbiased boosting with categorical features. arXiv."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/66\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T14:01:40Z","timestamp":1773064900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/3\/66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["make8030066"],"URL":"https:\/\/doi.org\/10.3390\/make8030066","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]}}}