Incremental multiple kernel extreme learning machine and its application in Robo-advisors

Xue, Jingming; Liu, Qiang; Li, Miaomiao; Liu, Xinwang; Ye, Yongkai; Wang, Siqi; Yin, Jianping

doi:10.1007/s00500-018-3031-2

Cited by 15 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, robo-advisors are also faced with challenges [15][16][17]. Previous studies of robo-advisors mainly focus on conceptual works [9,11,17], modification of algorithm and assets allocation method [18,19] and other development issues such as regulation [11,12]. Especially, from the perspective of trust, prior studies have identified some trust influencing factors of a robo-advisor, including security, information quality, interface design and so on [20,21].…”

Section: Robo-advisormentioning

confidence: 99%

“…Secondly, previous research of trust in robo-advisors generally concentrates on exploring the relationship between trust influencing factors and other customer behaviors such as adoption [18,19], rarely deeply investigating the trust developing mechanism of robo-advisors. Our study proposed an integrated trust building model and examined the relationship between trust influencing factors and trust in entities.…”

Section: Theoretical Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Trust Influencing Mechanism of Robo-Advisor Service: A Mixed Method Approach

et al. 2019

View full text Add to dashboard Cite

As a typical application of fintech, the robo-advisor has increasingly gained attention over the last decade. However, most research regarding the robo-advisor has focused on its development issues such as performance improvement and regulation, while limited research has paid attention to trust. This research extends the literature by investigating the trust influencing mechanism of robo-advisors by a mixed method approach. Specifically, we identified six salient trust influencing factors by qualitative interviews and proposed the research model based on trust transfer theory. This model was tested via a survey of 230 investors. Our study finds the significant influencing role of supervisory control and validates the relationships among trust influencing factors, trust in technologies, trust in vendor and trust in robo-advisor. Moreover, several differences between junior investors and senior investors are also found in our research. This study examines trust transfer theory in the new context of the robo-advisor and contributes to further development of this increasingly utilized service.

show abstract

Section: Robo-advisormentioning

confidence: 99%

Section: Theoretical Contributionmentioning

confidence: 99%

Exploring the Trust Influencing Mechanism of Robo-Advisor Service: A Mixed Method Approach

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For solving the financial time series forecasting problem, Huihui & Qun (2021) proposed an adaptive incremental ensemble learning (SIEL) algorithm with ELM as the base model while does not have more application in multi-scenario. Combining incremental learning and ELM, Xue et al (2018) proposed the incremental multiple kernel (IMK)-ELM algorithm and applied it to intelligent financial recommendation systems. For online sequences, Liang et al (2006) proposed an online sequential (OS)-ELM model, which first initializes the output weights of the network with a small number of training samples, and then acquires good online learning capability in the process of incremental learning.…”

Section: Related Workmentioning

confidence: 99%

ELM-KL-LSTM: a robust and general incremental learning method for efficient classification of time series data

Zhou,

Wang,

Huang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Efficiently analyzing and classifying dynamically changing time series data remains a challenge. The main issue lies in the significant differences in feature distribution that occur between old and new datasets generated constantly due to varying degrees of concept drift, anomalous data, erroneous data, high noise, and other factors. Taking into account the need to balance accuracy and efficiency when the distribution of the dataset changes, we proposed a new robust, generalized incremental learning (IL) model ELM-KL-LSTM. Extreme learning machine (ELM) is used as a lightweight pre-processing model which is updated using the new designed evaluation metrics based on Kullback-Leibler (KL) divergence values to measure the difference in feature distribution within sliding windows. Finally, we implemented efficient processing and classification analysis of dynamically changing time series data based on ELM lightweight pre-processing model, model update strategy and long short-term memory networks (LSTM) classification model. We conducted extensive experiments and comparation analysis based on the proposed method and benchmark methods in several different real application scenarios. Experimental results show that, compared with the benchmark methods, the proposed method exhibits good robustness and generalization in a number of different real-world application scenarios, and can successfully perform model updates and efficient classification analysis of incremental data with varying degrees improvement of classification accuracy. This provides and extends a new means for efficient analysis of dynamically changing time-series data.

show abstract

“…The use of robo-advisors for portfolio management (Park et al, 2016) is a recent literature trend. For example, Phoon and Koh (2017) provide easier and quicker access to digital loans through AI-based robo-advisors, while Xue et al (2018) show that ML techniques provide solid investment decisions through classification. Recently, Shanmuganathan (2020) reports the impressive performance of Robo pioneers such as Wealthfront and Bettermen (e.g., 2-year annualized returns of more than 5%).…”

Section: Impact On the Fintech Sectormentioning

confidence: 99%

Big data, artificial intelligence and machine learning: A transformative symbiosis in favour of financial technology

Nguyen

Sermpinis

Stasinakis

2022

Euro Fin Management

View full text Add to dashboard Cite

This paper uses a multidimensional descriptive analysis to familiarize the reader with the extent of penetration of big data, artificial intelligence (AI) and machine learning (ML) techniques in the financial technology roadmap. We propose a clear framework for the symbiotic nature of these data science themes towards fintech empowerment. The framework is validated through their impact on fintech, financial services' profession and the shifting paradigm of the data scientist role. We also discuss the dark side of this symbiosis, while AI and ML techniques are tied with the future challenges of AI ethics, regulation technology and the smart data utilization.

show abstract

Incremental multiple kernel extreme learning machine and its application in Robo-advisors

Cited by 15 publications

References 36 publications

Exploring the Trust Influencing Mechanism of Robo-Advisor Service: A Mixed Method Approach

Exploring the Trust Influencing Mechanism of Robo-Advisor Service: A Mixed Method Approach

ELM-KL-LSTM: a robust and general incremental learning method for efficient classification of time series data

Big data, artificial intelligence and machine learning: A transformative symbiosis in favour of financial technology

Contact Info

Product

Resources

About