Robo-Advising: A Dynamic Mean-Variance Approach

21 Pages Posted: 4 Jan 2021 Last revised: 7 Feb 2021

See all articles by Min Dai

Min Dai

The Hong Kong Polytechnic University

Hanqing Jin

Oxford-Nie Financial Big Data Laboratory; Mathematical Institute; St. Peter's College

Steven Kou

Boston University

Yuhong Xu

Soochow university

Date Written: October 29, 2020


In contrast to traditional financial advising, robo-advising needs to elicit investors’ risk profile via several simple online questions and provide advice consistent with conventional investment wisdom, e.g., rich and young people should invest more in risky assets. To meet the two challenges, we propose to do the asset allocation part of robo- advising using a dynamic mean-variance criterion over the the portfolio’s log-returns. The model yields analytical and time-consistent optimal portfolio policies under jump-diffusion models and regime-switching models.

Keywords: robo-advising, mean-variance, asset allocation

JEL Classification: G11, D81, C61

Suggested Citation

Dai, Min and Jin, Hanqing and Jin, Hanqing and Kou, Steven and Xu, Yuhong, Robo-Advising: A Dynamic Mean-Variance Approach (October 29, 2020). Available at SSRN: or

Min Dai (Contact Author)

The Hong Kong Polytechnic University ( email )

Hanqing Jin

Oxford-Nie Financial Big Data Laboratory ( email )

Andrew Wiles Building
Woodstock Road
Oxford, Oxfordshire OX2 6GG
United Kingdom

Mathematical Institute ( email )

Andrew Wiles Building
Radicliff Observatory Quarter, Woodstock Road
Oxford, oxfordshire OX2 6GG
United Kingdom


St. Peter's College ( email )

New Inn Hall Street
Oxford, Oxfordshire OX1 2DL
United Kingdom


Steven Kou

Boston University ( email )

595 Commonwealth Avenue
Boston, MA 02215
United States
6173583318 (Phone)

Yuhong Xu

Soochow university ( email )

No. 1 Shizi Street
Suzhou, Jiangsu 215006


Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics