Exhibition Data Analysis

The description states that "Exhibition Data Analysis" is a web-based application built to help exhibition professionals analyze data from spreadsheets using natural language and AI-assisted visualization. The author, Tom Choi, claims the tool supports uploading Excel or CSV files, preprocessing data, generating charts, and extracting business insights through conversational input.

The project appears to be a personal hackathon submission with no evidence of revenue, customers, or product-market fit beyond the author's own account. It is built using Python, Streamlit, Pandas, OpenAI APIs, and GitHub — with no indication of production deployment or user adoption.

The description states that the product is an "Exhibition Data Analysis App covering full pipeline from data load, preprocessing, visualization and insights with streamlit, github and supabase."

• It allows users to upload Excel or CSV files.
• It supports:
  • Data Load: Reviewing structure, missing values, descriptive statistics
  • Preprocessing: Cleaning missing values, duplicates, outliers, inconsistent data
  • Visualization: Creating statistical tables and charts
  • Business Insight:
    • Comparing visitor, exhibitor, satisfaction, marketing, consultation results
    • Asking analysis questions in natural language
    • Generating interpretations based on calculated results

The tool was built using Python, Pandas, Streamlit, Matplotlib, Pydantic, OpenAI API, and GitHub.

Inference: The product is a data analysis interface that uses AI to interpret natural-language queries and produce visualizations from uploaded datasets. It is not described as a SaaS offering or deployed in production.

The description states the following claims:

• Exhibition organizers collect valuable data but struggle to analyze it without programming knowledge.
• The tool helps exhibition professionals analyze data, create charts, and generate business insights through a simple web interface and natural-language conversation.
• It is not limited to exhibitions but also powerful for analyzing spreadsheet datasets.

Inference: The positioning evolved from solving an internal problem (data analysis for exhibitions) to a broader claim about helping any user analyze spreadsheets using AI. However, the description does not indicate whether this evolution reflects market feedback or just the author’s own vision.

The description states:

• Exhibition organizers who collect data from visitor registrations, surveys, booth scans, exhibitors, and consultations.
• The tool is intended for professionals in exhibition and conference settings.

Inference: The target customer segment appears to be event planners or organizers working with structured data. However, the description does not provide evidence of actual users or customer interviews.

The description does not state anything about pricing, monetization, or a business model.

Not evidenced

The description states:

• Built with Python, Pandas, Streamlit, Matplotlib, Pydantic, OpenAI API, GitHub.
• Uses GPT 5.6 and Codex to guide development.
• AI-generated chart code is structured via ChartSpec and validated before execution.
• Supports conversation history and state management in Streamlit.

Inference: The tool uses a combination of open-source libraries and AI APIs for data processing and visualization, with a focus on structured outputs and validation. It is not described as a scalable or hosted solution.

The description states:

• This was submitted to the OpenAI 2026 hackathon.
• The author claims to have learned that AI-powered analysis becomes more reliable when combined with structured outputs, validation, and actual calculation results.
• Future plans include predictive analysis, text analysis, automated reports, PPT/PDF exports, and a long-term goal of an AI-powered exhibition intelligence platform.

Not evidenced: No evidence of real users, revenue, or product adoption beyond the hackathon submission. The project is described as personal work with no indication of market traction or commercial viability.

The description does not mention any competitors or existing tools in this space.

Not evidenced

• The tool is a hackathon submission, not a product in production.
• No evidence of revenue, customers, or adoption.
• The author claims to have learned that domain knowledge is key — but the description does not show how the tool addresses this.
• The use of GPT 5.6 and Codex implies reliance on AI tools that may not be scalable or stable for commercial use.
• No indication of scalability, security, or data privacy features.

Inference: There is no evidence that this product has progressed beyond a prototype or personal project, raising questions about its readiness for market deployment or commercial viability.

1. Has the tool been tested with actual exhibition organizers or event planners?
2. What specific problems in data analysis do these users face that your tool solves?
3. Are there any existing tools in this space, and how does your approach differ?
4. How do you plan to scale beyond a single developer’s prototype?
5. What is the roadmap for monetization or product development?