arXiv subjects

Akira Kasuga

Publications and source records attributed to Akira Kasuga.

5 recordsLinked to original sources

arXiv2025

Enterprise Data Science Platform: A Unified Architecture for Federated Data Access

Organizations struggle to share data across departments that have adopted different data analytics platforms. If n datasets must serve m environments, up to n*m replicas can emerge, increasing inconsistency and cost. Traditional warehouses copy data into vendor-specific stores; cross-platform access is hard. This study proposes the Enterprise Data Science Platform (EDSP), which builds on data lakehouse architecture and follows a Write-Once, Read-Anywhere principle. EDSP enables federated data access for multi-query engine environments, targeting data science workloads with periodic data updates and query response times ranging from seconds to minutes. By providing centralized data management with federated access from multiple query engines to the same data sources, EDSP eliminates data duplication and vendor lock-in inherent in traditional data warehouses. The platform employs a four-layer architecture: Data Preparation, Data Store, Access Interface, and Query Engines. This design enforces separation of concerns and reduces the need for data migration when integrating additional analytical environments. Experimental results demonstrate that major cloud data warehouses and programming environments can directly query EDSP-managed datasets. We implemented and deployed EDSP in production, confirming interoperability across multiple query engines. For data sharing across different analytical environments, EDSP achieves a 33-44% reduction in operational steps compared with conventional approaches requiring data migration. Although query latency may increase by up to a factor of 2.6 compared with native tables, end-to-end completion times remain on the order of seconds, maintaining practical performance for analytical use cases. Based on our production experience, EDSP provides practical design guidelines for addressing the data-silo problem in multi-query engine environments.

cs.DB↗

arXiv2025

System-driven Interactive Design Support for Cloud Architecture: A Qualitative User Experience Study with Novice Engineers

Cloud architecture design presents significant challenges due to the necessity of clarifying ambiguous requirements and systematically addressing complex trade-offs, especially for novice engineers with limited cloud experience. While recent advances in the use of AI tools have broadened available options, system-driven approaches that offer explicit guidance and step-by-step information management may be especially effective in supporting novices during the design process. This study qualitatively examines the experiences of 60 novice engineers using such a system-driven cloud design support tool. The findings indicate that structured and proactive system guidance helps novices engage more effectively in architectural design, especially when addressing tasks where knowledge and experience gaps are most critical. For example, participants found it easier to create initial architectures and did not need to craft prompts themselves. In addition, participants reported that the ability to simulate and compare multiple architecture options enabled them to deepen their understanding of cloud design principles and trade-offs, demonstrating the educational value of system-driven support. The study also identifies areas for improvement, including more adaptive information delivery tailored to user expertise, mechanisms for validating system outputs, and better integration with implementation workflows such as infrastructure-as-code generation and deployment guidance. Addressing these aspects can further enhance the educational and practical value of system-driven support tools for cloud architecture design.

cs.HC↗

arXiv2025

MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering

This paper presents MobQA, a benchmark dataset designed to evaluate the semantic understanding capabilities of large language models (LLMs) for human mobility data through natural language question answering. While existing models excel at predicting human movement patterns, it remains unobvious how much they can interpret the underlying reasons or semantic meaning of those patterns. MobQA provides a comprehensive evaluation framework for LLMs to answer questions about diverse human GPS trajectories spanning daily to weekly granularities. It comprises 5,800 high-quality question-answer pairs across three complementary question types: factual retrieval (precise data extraction), multiple-choice reasoning (semantic inference), and free-form explanation (interpretive description), which all require spatial, temporal, and semantic reasoning. Our evaluation of major LLMs reveals strong performance on factual retrieval but significant limitations in semantic reasoning and explanation question answering, with trajectory length substantially impacting model effectiveness. These findings demonstrate the achievements and limitations of state-of-the-art LLMs for semantic mobility understanding.\footnote{MobQA dataset is available at https://github.com/CyberAgentAILab/mobqa.}

cs.CL↗

arXiv2025

System-driven Cloud Architecture Design Support with Structured State Management and Guided Decision Assistance

Cloud architecture design is a complex process requiring both technical expertise and architectural knowledge to develop solutions from frequently ambiguous requirements. We present CloudArchitectBuddy, a system-driven cloud architecture design support application with two key mechanisms: (1) structured state management that enhances design understanding through explicit representation of requirements and architectural decisions, and (2) guided decision assistance that facilitates design progress through proactive verification and requirement refinement. Our study with 16 industry practitioners showed that while our approach achieved comparable design quality to a chat interface, participants rated our system higher for usability and appreciated its ability to help understand architectural relationships and identify missing requirements. However, participants also expressed a need for user-initiated interactions where they could freely provide design instructions and engage in detailed discussions with LLMs. These results suggest that integrating a chat interface into our structured and guided workflow approach would create a more practical solution, balancing systematic design support with conversational flexibility for comprehensive cloud architecture development.

cs.SE↗

arXiv2024

CXSimulator: A User Behavior Simulation using LLM Embeddings for Web-Marketing Campaign Assessment

This paper presents the Customer Experience (CX) Simulator, a novel framework designed to assess the effects of untested web-marketing campaigns through user behavior simulations. The proposed framework leverages large language models (LLMs) to represent various events in a user's behavioral history, such as viewing an item, applying a coupon, or purchasing an item, as semantic embedding vectors. We train a model to predict transitions between events from their LLM embeddings, which can even generalize to unseen events by learning from diverse training data. In web-marketing applications, we leverage this transition prediction model to simulate how users might react differently when new campaigns or products are presented to them. This allows us to eliminate the need for costly online testing and enhance the marketers' abilities to reveal insights. Our numerical evaluation and user study, utilizing BigQuery Public Datasets from the Google Merchandise Store, demonstrate the effectiveness of our framework.

cs.LG↗