quantopian · cfenaroli · Jul 20, 2017 · Jul 25, 2017 · Aug 1, 2017 · Aug 3, 2017
diff --git a/notebooks/lectures/Combining_Independent_Signals/notebook.ipynb b/notebooks/lectures/Combining_Independent_Signals/notebook.ipynb
diff --git a/notebooks/lectures/Model_Ensembling/copy.txt b/notebooks/lectures/Model_Ensembling/copy.txt
@@ -0,0 +1 @@
+A statistical model is an attempt to represent reality data using numbers. A well-founded model can be used to explain observed relationships between variables, or extrapolate these relationships in order to make predictions. For any given problem, there are practically infinite ways to approach it using statistical models, each with a unique perspective on the task at hand. By combining many independent models, using methods as simple as averaging their outputs, you can create an ensemble with more predictive power than any of its components alone. This notebook focuses on the intuition behind ensembling, demonstrating its effectiveness through simulations and theory, and concludes with an real-life example on modeling the price of IWM, an ETF that tracks the Russel-2000 index.
diff --git a/notebooks/lectures/Model_Ensembling/notebook.ipynb b/notebooks/lectures/Model_Ensembling/notebook.ipynb
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		A statistical model is an attempt to represent reality data using numbers. A well-founded model can be used to explain observed relationships between variables, or extrapolate these relationships in order to make predictions. For any given problem, there are practically infinite ways to approach it using statistical models, each with a unique perspective on the task at hand. By combining many independent models, using methods as simple as averaging their outputs, you can create an ensemble with more predictive power than any of its components alone. This notebook focuses on the intuition behind ensembling, demonstrating its effectiveness through simulations and theory, and concludes with an real-life example on modeling the price of IWM, an ETF that tracks the Russel-2000 index.