Krahasoni metodat

	Parashikimi Konform për Parashikimin e Serive Kohore	Përmbledhja me Gradient (Gradient Boosting)	Regresioni kuantil
Fusha	Ekonometri	Mësimi i makinës	Ekonometri
Familja	Regression model	Machine learning	Regression model
Viti i origjinës	2021	2001	1978
Krijuesi	Angelopoulos & Bates (tutorial); Xu & Xie (time-series EnbPI)	Friedman, J. H.	Koenker & Bassett
Lloji	Distribution-free prediction interval wrapper	Ensemble (sequential boosting of decision trees)	Conditional quantile regression
Burimi themelues	Angelopoulos, A. N. & Bates, S. (2023). Conformal Prediction: A Gentle Introduction. Foundations and Trends in Machine Learning, 16(4), 494-591.	Friedman, J. H. (2001). Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 29(5), 1189–1232.	Koenker, R. & Bassett, G., Jr. (1978). Regression Quantiles. Econometrica, 46(1), 33-50.
Emërtime të tjera	conformal prediction, distribution-free prediction intervals, EnbPI, Konformal Tahmin (Conformal Prediction — Zaman Serisi)	Gradient Boosting (GBM), GBM, gradient boosted trees, gradient boosting machine	conditional quantile regression, regression quantiles, Kantil Regresyon
Të lidhura	4	5	5
Përmbledhja	Conformal prediction is a distribution-free wrapper that turns any point forecaster — ARIMA, a neural network, or a machine-learning model — into valid prediction intervals using only its residuals. The time-series form was popularised by Xu & Xie (2021) and the modern tutorial treatment by Angelopoulos & Bates (2023).	Gradient Boosting is an ensemble learning method, formalised by Jerome H. Friedman in 2001, that combines a sequence of weak learners — typically shallow decision trees — so that each new tree is fitted to minimise the residual errors of the trees before it. It is the core algorithm behind popular implementations such as XGBoost, LightGBM and CatBoost.	Quantile regression models conditional quantiles of an outcome - the median, the 25th or 75th percentile, and so on - rather than the conditional mean that OLS targets. Introduced by Koenker and Bassett in 1978, it reveals how predictors act across the whole distribution, including its tails.