Artificial Intelligence Alter Egos: Who might benefit from robo-investing?

D’Hondt, Catherine; Winne, Rudy De; Ghysels, Éric; Raymond, Steve

doi:10.1016/j.jempfin.2020.10.002

Cited by 34 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies investigated Robo-advisors impact on the change of behavioural biases in general (Bhatia et al, 2020;Braeuer et al, 2017;Rohner, 2018). A few studies focused on Robo-advisors effect on specific behavioural biases: disposition effect, trend-chasing and rank effect (D' Acunto et al, 2019), home bias (Loos et al, 2020, disposition effect (D'Hondt, 2019;Liaudinskas, 2019), decision inertia . Based on the literature review, we can conclude that research on Robo-advisors role and effects on behavioural biases in the investment area is still limited and focuses mainly on examining a limited number of behavioural biases.…”

Section: Conclusion and Implications For Future Researchmentioning

confidence: 99%

Linking the Robo-advisors Phenomenon and Behavioural Biases in Investment Management: An Interdisciplinary Literature Review and Research Agenda

Lisauskiene

Darškuvienė

2021

OMEE

View full text Add to dashboard Cite

Technological advancements bring continuous changes into the investment industry. The paper aims to provide insights on future research agenda based on a review of the current stance of research on the links between the Robo-advisors phenomenon and behavioural biases of individual investors. A qualitative investigation method has been applied for literature review on Robo-advisors and their impact on behavioural biases. The key findings indicate that Robo-advisors can help users to make better informed and less biased decisions. However, Robo-advisors activate the investors’ automatic system processes. The resulting passive investment approach could lead to alienation of the investors from the stock market, decreasing their understanding of the investment process that could widen a gap between different clusters of investors. The paper makes several contributions to the literature. First, it provides arguments on why a dual process theoretical framework in the relationship between financial advisory and investment behavioural biases is applicable. Second, it studies the Robo-advisor phenomenon and proposes a comprehensive definition of Robo-advisors. Third, the literature review suggests drivers of the Robo-advisors effect on the changes of behavioural biases as a future research direction.

show abstract

Section: Conclusion and Implications For Future Researchmentioning

confidence: 99%

Linking the Robo-advisors Phenomenon and Behavioural Biases in Investment Management: An Interdisciplinary Literature Review and Research Agenda

Lisauskiene

Darškuvienė

2021

OMEE

View full text Add to dashboard Cite

show abstract

“…How to construct a stock factor strategy is an open problem with long history in portfolio management. From Wang et al (2012) invented the N-LASR to Fiévet and Sornette (2018) proposed a decision tree forecasting model, and Gu et al (2020) andD'Hondt et al (2020) gave a comprehensive analysis of machine learning methods for the canonical problem of empirical asset pricing, all of them agree that it may improve the strategy performance if the prediction model can dig out nonlinear and complex information.…”

Section: Definition 8 (Comonotonic Populationmentioning

confidence: 99%

“…Rasekhschaffe and Jones (2019) provided an example of the machine learning techniques to forecast the cross-section of stock returns. Gu et al (2020) andD'Hondt et al (2020) gave comprehensive analysis of machine learning methods for the canonical problem of empirical asset pricing, attributing their predicted gains to the non-linearity.…”

Section: Introductionmentioning

confidence: 99%

The Success of AdaBoost and Its Application in Portfolio Management

Chuan

Zhao

et al. 2021

Preprint

View full text Add to dashboard Cite

We develop a novel approach to explain why AdaBoost is a successful classifier.By introducing a measure of the influence of the noise points (ION) in the training data for the binary classification problem, we prove that there is a strong connection between the ION and the test error. We further identify that the ION of AdaBoost decreases as the iteration number or the complexity of the base learners increases. We confirm that it is impossible to obtain a consistent classifier without deep trees as the base learners of AdaBoost in some complicated situations. We apply AdaBoost in portfolio management via empirical studies in the Chinese market, which corroborates our theoretical propositions.

show abstract

“…Specifically, we consider the popular Bayesian model averaging (BMA), weighted‐average least squares (WALS) introduced by Magnus, Powell, and Prüfer (), Mallows model averaging (MMA) proposed by Hansen (, ), jackknife model averaging (JMA) proposed by Hansen and Racine (), and the standard multivariate predictive regression known as the kitchen sink model. We also consider popular machine learning algorithms, such as LASSO, proposed by Tibshirani (), and elastic net, introduced by Zou and Hastie (), both of which are useful in forecasting stock returns, as recently demonstrated by Gu, Kelly, and Xiu () and D'Hondt, Winne, Ghysels, and Raymond ().…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Gu et al () conduct a comprehensive analysis of machine learning methods for forecasting equity premia and show that machine learning improves predictions relative to traditional methods. D'Hondt et al () utilize various machine learning methods and a unique data set of investors' brokerage accounts to assess the potential benefits of robo‐investing. They find that machine learning results in significant investment performance improvements for certain segments of investors, in particular those with low income and/or low education.…”

Section: Introductionmentioning

confidence: 99%

Forecasting stock returns with model uncertainty and parameter instability

Zhang

Jacobsen

et al. 2020

J of Applied Econometrics

View full text Add to dashboard Cite

Summary We compare several representative sophisticated model averaging and variable selection techniques of forecasting stock returns. When estimated traditionally, our results confirm that the simple combination of individual predictors is superior. However, sophisticated models improve dramatically once we combine them with the historical average and take parameter instability into account. An equal weighted combination of the historical average with the standard multivariate predictive regression estimated using the average windows method, for example, achieves a statistically significant monthly out‐of‐sample ROS2 of 1.10% and annual utility gains of 2.34%. We obtain similar gains for predicting future macroeconomic conditions.

show abstract

Artificial Intelligence Alter Egos: Who might benefit from robo-investing?

Cited by 34 publications

References 12 publications

Linking the Robo-advisors Phenomenon and Behavioural Biases in Investment Management: An Interdisciplinary Literature Review and Research Agenda

Linking the Robo-advisors Phenomenon and Behavioural Biases in Investment Management: An Interdisciplinary Literature Review and Research Agenda

The Success of AdaBoost and Its Application in Portfolio Management

Forecasting stock returns with model uncertainty and parameter instability

Contact Info

Product

Resources

About