Boreiko Dmitri, Massarotti Francesca
Faculty of Economics and Management, Free University of Bozen-Bolzano, Bolzano, Italy.
Frankfurt School of Finance and Management, Frankfurt, Germany.
Front Artif Intell. 2020 Sep 18;3:60. doi: 10.3389/frai.2020.00060. eCollection 2020.
Automated financial advising (robo-advising) has become an established practice in wealth management, yet very few studies have looked at the cross-section of the robo-advisors and the factors explaining the persistent variability in their portfolio allocation recommendations. Using a sample of 53 advising platforms from the US and Germany, we show that the underlying algorithms manage to identify different risk profiles, although substantial variability is evident even within the same investor types' groups. The robo-advisor expertise in a particular asset class seems to play a significant role, as does the geographical location, while the breadth of the offered investment choice (number of portfolios) across the robo-advisors under study does not seem to have an effect.
自动化财务建议（智能投顾）已成为财富管理中的既定做法，但很少有研究考察智能投顾的全貌以及解释其投资组合配置建议持续存在差异的因素。我们以美国和德国的53个建议平台为样本，发现底层算法能够识别不同的风险状况，尽管即使在同一投资者类型组内也存在明显的差异。智能投顾在特定资产类别的专业知识似乎起着重要作用，地理位置也是如此，而在所研究的智能投顾中，所提供投资选择的广度（投资组合数量）似乎没有影响。
