Modeling Investor Behavior Using Machine Learning: Mean-Reversion and Momentum Trading Strategies

Table 4

This table reports output from Regression (6). We ask whether investors with higher academic degree have different sensitiveness with respect to their investment portfolio to IBOVESPA index changes. We only use changes rather than past averages because the former has greater prediction power as reported by our feature selection procedure. The dependent variable is the variation of portfolio investment volume of investor i at time t in the Brazilian stock market from the beginning of 2016 to the end of 2018. Regressors are 1- (1), 2- (2), 3- (3), 5- (4), and 30-day (5) IBOVESPA index variations, as well as their interaction with the investor’s academic degree. The panel is on a daily frequency basis. Following Petersen [50]; we double-cluster standard errors at the investor and time levels. Significance levels: , , .

Dependent variable	Investor portfolio volume variation ()
	(1)	(2)	(3)	(4)	(5)
Regressor with
1-day variation	−10.347
	(1.795)
2-day variation		−5.136
		(1.299)
3-day variation			−2.750
			(1.076)
5-day variation				−2.565
				(0.931)
30-day variation					0.085
					(0.695)
Interactions of with academic degree
1-day variation Higher education	5.347
	(1.520)
2-day variation Higher education		3.915
		(1.040)
3-day variation Higher education			2.864
			(1.573)
5-day variation Higher education				2.471
				(1.398)
30-day variation Higher education					−0.237
					(0.647)
Fixed effects
Investor	Yes	Yes	Yes	Yes	Yes
Month-year	Yes	Yes	Yes	Yes	Yes
Observations	356,172	355,796	355,419	354,588	343,592
R^2	0.038	0.036	0.036	0.035	0.035
Error clustering	Investor	Investor	Investor	Investor	Investor
	Time	Time	Time	Time	Time