📌 AI Trading Screener – Portfolio & RFQ Case Study - DEMO

Product Title

Raghav4Web AI Trading Screener

Product Description

The AI Trading Screener is a next-generation financial analysis tool built using Google AiStudio. It empowers traders, investors, and portfolio managers to filter and analyze assets (stocks, ETFs, crypto, bonds, futures, forex, etc.) using fundamental, technical, and descriptive parameters.
Users can view interactive AI-powered insights including trend charts, technical analysis, seasonal patterns, and company profiles, enabling data-driven investment decisions.

UX Process

The design followed a human-centered, mobile-first UX approach ensuring both beginner and expert traders find value:

1. User Research & Personas – Identified primary user groups: retail investors, financial advisors, and day traders.

2. Problem Framing – Users struggle with overloaded data and lack of custom filters for screening investments quickly.

3. Information Architecture – Created a simple left-to-right flow: Filter → Results → Analysis → Action.

4. Wireframing & Prototyping – Low-fidelity prototypes in Figma, refined with usability feedback.

5. Usability Testing – Conducted task-based tests with 8 users to validate clarity of filters, chart interactions, and responsive layouts.

6. UI Design – Dark theme for trader-friendly viewing, AI-generated insights cards, and modular filter panels.

UX Research Methods

• Surveys & Interviews with active retail investors.

• Competitive Benchmarking (TradingView, Finviz, Yahoo Finance).

• Card Sorting to prioritize filters (Market Cap, P/E, RSI, Beta).

• Think-Aloud Testing to refine navigation and terminology.

• Heuristic Evaluation for accessibility and mobile performance.

Technology Stack

• Frontend: React.js, Next.js, TailwindCSS (for responsive UI).

• Backend: Node.js + Express for API orchestration.

• AI/ML: Google AiStudio models for financial data classification, NLP for sentiment analysis.

• Database: PostgreSQL (structured financial data), Redis (caching).

• APIs/Data Sources: Alpha Vantage, Yahoo Finance API, Trading Economics.

• Charts & Visualization: Recharts, D3.js, Plotly.

• Deployment: Docker + Kubernetes on Google Cloud (GCP).

• Auth & Security: OAuth2, JWT, HTTPS/TLS.

1-Page Case Study (Portfolio / RFQ Format)

Problem

Traders and investors face information overload across multiple platforms. They need a unified AI-powered tool that filters assets with customizable criteria and provides actionable insights in real-time.

Solution

We designed and built the AI Trading Screener that combines descriptive, fundamental, and technical filters with AI-driven insights. The application reduces decision-making time, increases portfolio transparency, and improves trading confidence.

Design Process

1. Research – Identified core filters and user needs through interviews, surveys, and benchmarking.

2. Ideation – Explored multiple filter combinations and visualization methods.

3. Wireframing & Testing – Created Figma prototypes, conducted A/B tests on filter layout.

4. UI/UX Design – Finalized a dark-themed modular design with responsive charts and AI insights.

5. Iteration – Continuous improvements based on user testing and feedback.

Final Product

• Dynamic Asset Screener (stocks, ETFs, futures, crypto, bonds, forex).

• Filter by fundamentals & technicals (P/E, RSI, Beta, Dividend Yield).

• Interactive Charts & Analysis (Seasonality, Technicals, Profiles).

• AI-Powered Insights (sentiment trends, anomalies detection).

• Cross-Platform – Web-first, mobile responsive.