analytics
Portafolio de Iván
Projects chevron_right AI Data Analyst Platform
smart_toy Applied AI database SQL monitoring Analytics

AI Data Analyst Platform

Conversational analytics platform designed as a "ChatGPT for data analysis": it turns natural-language questions into safe SQL, automated analysis, interactive visualizations, insights, and predictive outputs.

Stack

FastAPI Streamlit Python SQLAlchemy Plotly scikit-learn OpenAI API
flag

Objective

Build an end-to-end analytics product where users can upload data, ask business questions in natural language, and automatically receive SQL, analysis, charts, recommendations, and predictive outputs.

account_tree

Architecture

  1. Streamlit frontend for dataset upload, natural-language questions, charts, and report downloads.
  2. FastAPI backend exposing query, dataset registration, insight history, and chart endpoints.
  3. Specialized agent system for orchestration, SQL generation, analysis, visualization, and insights.
  4. Data layer compatible with CSV, SQLite, and PostgreSQL.
  5. Machine learning services for forecasting, clustering, and anomaly detection.
auto_graph

Key capabilities

Natural Language to SQL

Interprets business questions and generates safe read-only SQL queries.

Automated EDA

Builds profiling, descriptive statistics, missing-value reports, correlations, and outlier checks automatically.

Smart visualization

Selects chart types automatically and delivers interactive Plotly outputs.

Prediction and anomalies

Extends analysis with forecasting, clustering, and anomaly detection workflows.

image

Screenshots

AI Data Analyst Platform frontend screenshot
Streamlit workspace with natural-language query, analysis, and previewed results.
FastAPI Swagger documentation
Documented API surface in Swagger for queries, datasets, charts, and insights.
workspace_premium

Outcome

This project demonstrates product thinking, backend architecture, LLM integration, visualization, operational security, and VPS deployment. It is a strong flagship piece because it shows the ability to build complete analytics products, not just isolated dashboards.