Personalization Data Research Articles

Comparative Analysis of Traditional Wealth Management Services vs. AI-Based Wealth Management Software

The integration of artificial intelligence (AI) is transforming the wealth management industry. This paper compares traditional wealth management with AI-based solutions to assess their value to customers, focusing on factors like cost, customization, accessibility, performance, and accuracy. Traditional wealth management offers personalized human interaction, expert advice, and tailored financial planning but often comes with higher costs and limited scalability. In contrast, AI-based wealth management uses advanced algorithms and data analytics for scalable, efficient, and cost-effective services, though it may lack the personal touch of human advisors. The study finds that traditional wealth management excels in comprehensive planning and trust-based relationships, crucial for clients with complex needs. AI-driven solutions enhance accessibility and affordability, providing sophisticated insights to a wider audience. However, concerns about personalization quality and data reliance remain. The research suggests that a hybrid model combining traditional and AI-based approaches may offer the best solution, leveraging AI’s efficiency while maintaining personalized service and expert advice. Overall, this paper provides valuable insights for financial planners, identifying strategies to enhance value in the evolving wealth management field. Keywords: Wealth Management, Artificial Intelligence (AI), Financial Planning, AI-based Solutions, Personalized Financial Advice, Hybrid Wealth Management.

Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward

Large language model-based explainable recommendation (LLM-based ER) systems can provide remarkable human-like explanations and have widely received attention from researchers. However, the original LLM-based ER systems face three low-quality problems in their generated explanations, i.e., lack of personalization, inconsistency, and questionable explanation data. To address these problems, we propose a novel LLM-based ER model denoted as LLM2ER to serve as a backbone and devise two innovative explainable quality reward models for fine-tuning such a backbone in a reinforcement learning paradigm, ultimately yielding a fine-tuned model denoted as LLM2ER-EQR, which can provide high-quality explanations. LLM2ER-EQR can generate personalized, informative, and consistent high-quality explanations learned from questionable-quality explanation datasets. Extensive experiments conducted on three real-world datasets demonstrate that our model can generate fluent, diverse, informative, and highly personalized explanations.

Journey tracker: driver alerting system with a deep learning approach.

Negligence of public transport drivers due to drowsiness poses risks not only to their own lives but also to the lives of passengers. The designed journey tracker system alerts the drivers and activates potential penalties. A custom EfficientNet model architecture, based on EfficientNet design principles, is built and trained using the Media Research Lab (MRL) eye dataset. Reflections in frames are filtered out to ensure accurate detections. A 10 min initial period is utilized to understand the driver's baseline behavior, enhancing the reliability of drowsiness detections. Input from drivers is considered to determine the frame rate for more precise real-time monitoring. Only the eye regions of individual drivers are captured to maintain privacy and ethical standards, fostering driver comfort. Hyperparameter tuning and testing of different activation functions during model training aim to strike a balance between model complexity, performance and computational cost. Obtained an accuracy rate of 95% and results demonstrate that the "swish" activation function outperforms ReLU, sigmoid and tanh activation functions in extracting hierarchical features. Additionally, models trained from scratch exhibit superior performance compared to pretrained models. This system promotes safer public transportation and enhances professionalism by monitoring driver alertness. The system detects closed eyes and performs a cross-reference using personalization data and pupil detection to trigger appropriate alerts and impose penalties.

Interactive Data Comics

This paper investigates how to make data comics interactive. Data comics are an effective and versatile means for visual communication, leveraging the power of sequential narration and combined textual and visual content, while providing an overview of the storyline through panels assembled in expressive layouts. While a powerful static storytelling medium that works well on paper support, adding interactivity to data comics can enable non-linear storytelling, personalization, levels of details, explanations, and potentially enriched user experiences. This paper introduces a set of operations tailored to support data comics narrative goals that go beyond the traditional linear, immutable storyline curated by a story author. The goals and operations include adding and removing panels into pre-defined layouts to support branching, change of perspective, or access to detail-on-demand, as well as providing and modifying data, and interacting with data representation, to support personalization and reader-defined data focus. We propose a lightweight specification language, COMICSCRIPT, for designers to add such interactivity to static comics. To assess the viability of our authoring process, we recruited six professional illustrators, designers and data comics enthusiasts and asked them to craft an interactive comic, allowing us to understand authoring workflow and potential of our approach. We present examples of interactive comics in a gallery. This initial step towards understanding the design space of interactive comics can inform the design of creation tools and experiences for interactive storytelling.

Public attitudes towards algorithmic personalization and use of personal data online: evidence from Germany, Great Britain, and the United States

People rely on data-driven AI technologies nearly every time they go online, whether they are shopping, scrolling through news feeds, or looking for entertainment. Yet despite their ubiquity, personalization algorithms and the associated large-scale collection of personal data have largely escaped public scrutiny. Policy makers who wish to introduce regulations that respect people’s attitudes towards privacy and algorithmic personalization on the Internet would greatly benefit from knowing how people perceive personalization and personal data collection. To contribute to an empirical foundation for this knowledge, we surveyed public attitudes towards key aspects of algorithmic personalization and people’s data privacy concerns and behavior using representative online samples in Germany (N = 1065), Great Britain (N = 1092), and the United States (N = 1059). Our findings show that people object to the collection and use of sensitive personal information and to the personalization of political campaigning and, in Germany and Great Britain, to the personalization of news sources. Encouragingly, attitudes are independent of political preferences: People across the political spectrum share the same concerns about their data privacy and show similar levels of acceptance regarding personalized digital services and the use of private data for personalization. We also found an acceptability gap: People are more accepting of personalized services than of the collection of personal data and information required for these services. A large majority of respondents rated, on average, personalized services as more acceptable than the collection of personal information or data. The acceptability gap can be observed at both the aggregate and the individual level. Across countries, between 64% and 75% of respondents showed an acceptability gap. Our findings suggest a need for transparent algorithmic personalization that minimizes use of personal data, respects people’s preferences on personalization, is easy to adjust, and does not extend to political advertising.

Personalized automatic sleep staging with single-night data: a pilot study with Kullback–Leibler divergence regularization

Objective: Brain waves vary between people. This work aims to improve automatic sleep staging for longitudinal sleep monitoring via personalization of algorithms based on individual characteristics extracted from sleep data recorded during the first night. Approach: As data from a single night are very small, thereby making model training difficult, we propose a Kullback–Leibler (KL) divergence regularized transfer learning approach to address this problem. We employ the pretrained SeqSleepNet (i.e. the subject independent model) as a starting point and finetune it with the single-night personalization data to derive the personalized model. This is done by adding the KL divergence between the output of the subject independent model and it of the personalized model to the loss function during finetuning. In effect, KL-divergence regularization prevents the personalized model from overfitting to the single-night data and straying too far away from the subject independent model. Main results: Experimental results on the Sleep-EDF Expanded database consisting of 75 subjects show that sleep staging personalization with single-night data is possible with help of the proposed KL-divergence regularization. On average, we achieve a personalized sleep staging accuracy of 79.6%, a Cohen’s kappa of 0.706, a macro F1-score of 73.0%, a sensitivity of 71.8%, and a specificity of 94.2%. Significance: We find both that the approach is robust against overfitting and that it improves the accuracy by 4.5 percentage points compared to the baseline method without personalization and 2.2 percentage points compared to it with personalization but without regularization.

When Simpler Data Does Not Imply Less Information

The exponential growth in smartphone adoption is contributing to the availability of vast amounts of human behavioral data. This data enables the development of increasingly accurate data-driven user models that facilitate the delivery of personalized services that are often free in exchange for the use of its customers’ data. Although such usage conventions have raised many privacy concerns, the increasing value of personal data is motivating diverse entities to aggressively collect and exploit the data. In this article, we unfold profiling scenarios around mobile HTTP(S) traffic, focusing on those that have limited but meaningful segments of the data. The capability of the scenarios to profile personal information is examined with real user data, collected in the wild from 61 mobile phone users for a minimum of 30 days. Our study attempts to model heterogeneous user traits and interests, including personality, boredom proneness, demographics, and shopping interests. Based on our modeling results, we discuss various implications to personalization, privacy, and personal data rights.

TTA.KO-07.0079 XCAS 프로토콜 A.1의 CAS 서비스 분리를 통한 CAS Client 개인화 메커니즘

CAS Client 개인화는 CAS Client의 식별을 위해서 CAS Client에 CAS ID나 Key를 발급하는 것으로 CAS 운영을 위해 중요한 기술이다. TTA.KO-07.0079 XCAS에서 프로토콜 A.1은 XCAS Server에서 CAS Server로부터 전달 받은 CAS Client 개인화 데이터를 미리 저장해 놓고, XCAS HOST의 요청에 따라 개인화 데이터를 전송하여 CAS Client 개인화를 수행한다. 하지만, 이러한 방법은 CAS의 서비스 영역을 XCAS에서 수행하게 하여 XCAS Server에 CAS Client 이미지 관리와 네트워크 트래픽을 가중시키는 단점이 있다. 본 논문에서는 TTA XCAS A.1의 이러한 단점을 보완하기 위하여 XCAS Server에서 CAS의 서비스 영역을 분리하고, CAS Client 개인화를 CAS Server에서 이루어지게 하여 XCAS Server의 이미지관리 및 네트워크 트래픽을 분산시켰다. CAS Client personalization means to issue CAS ID or Key for CAS service, which is Core Technology for CAS operation. Protocol A.1 on TTA.KR-07.0079 XCAS, stores CAS Client personalization data from CAS server in XCAS server, and transmits the personalization data by request of XCAS HOST for CAS Client personalization. However, this may increase Network Traffic and CAS Client image management in XCAS server. In this thesis, to complement this, CAS Client personalization is executed on CAS Server by separating CAS service field. Therefore this can distribute Image management and Network Traffic of XCAS server.

Case study: the Health SmartLibrary experiences in web personalization and customization at the Galter Health Sciences Library, Northwestern University

How can the user's access to health information, especially full-text articles, be improved? The solution is building and evaluating the Health SmartLibrary (HSL). The setting is the Galter Health Sciences Library, Feinberg School of Medicine, Northwestern University. The HSL was built on web-based personalization and customization tools: My E-Resources, Stay Current, Quick Search, and File Cabinet. Personalization and customization data were tracked to show user activity with these value-added, online services. Registration data indicated that users were receptive to personalized resource selection and that the automated application of specialty-based, personalized HSLs was more frequently adopted than manual customization by users. Those who did customize customized My E-Resources and Stay Current more often than Quick Search and File Cabinet. Most of those who customized did so only once. Users did not always take advantage of the services designed to aid their library research experiences. When personalization is available at registration, users readily accepted it. Customization tools were used less frequently; however, more research is needed to determine why this was the case.

Comparing different quality models for portals

Purpose – The purpose of this research is to present a brief overview of some proposals for portal quality models. In addition, a comparative study is carried out to determine the similarities and differences of these models. Design/methodology/approach – In order to compare the different portal quality models, their main characteristics were analysed as well as the different dimensions proposed in each model. Findings – As a result, several similarities and differences have been established among the portal quality models. For example, the dimensions present in all the models are navigation, representation, personalization and intrinsic data quality. This means that, as expected, it was found that researchers pay special attention to visual aspects. Practical implications – The comparison attempts to determine which aspects are important for the quality of a web portal, and also to clarify which proposal is the most broadly relevant. The paper also identifies, where necessary, what features must be added in order to ensure that all aspects related to web portal quality are considered. Originality/value – This work tries to identify a portal quality model that can be used to gauge portal quality levels. The model could also be used where there is a low quality level for a particular dimension, giving some guidelines for improving the weaker aspects.