Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/JoseOlivares19/Proyecto-PC3-JavaScript-Avanzado/llms.txt

Use this file to discover all available pages before exploring further.

SmartStock360 is an AI-powered inventory and business intelligence platform built on a three-tier architecture. A React frontend communicates with a Spring Boot middleware layer, which in turn calls a Python FastAPI service running five in-memory Random Forest classifiers — covering demand forecasting, fraud detection, cybersecurity risk, academic performance, and talent matching.

Introduction

Understand what SmartStock360 does and the problems it solves.

Architecture

Explore the three-tier system design: React → Spring Boot → Python FastAPI.

Quickstart

Get all three services running locally in minutes.

AI Models Service

Learn about the five ML models powering SmartStock360’s predictions.

​
What SmartStock360 Provides

SmartStock360 ships five AI-powered prediction endpoints, each backed by a Random Forest classifier trained in-memory at startup. No external model hosting or API keys are required.

Smart Stock 360

Predict product demand and get replenishment recommendations.

Fraud Shield

Classify financial transactions as safe, suspicious, or fraudulent.

Cyber Sentinel

Score cybersecurity incident severity across network and host metrics.

UTP Risk AI

Evaluate student academic risk based on performance indicators.

Talent Match AI

Match tech candidates to Frontend, Backend, Data, or Fullstack profiles.

API Reference

Full reference for all Spring Boot and Python FastAPI endpoints.

​
Get Up and Running

1

Start the Python AI Service

Install dependencies and launch the FastAPI server on port 8001. All five models train automatically at startup.
cd update/Kit_Python_Modelos_IA_JavaScript_Avanzado_S15_UTP
pip install -r requirements.txt
uvicorn app:app --reload --port 8001
2

Configure and Start Spring Boot

Set up a MySQL database named smartstock, update application.properties, and run the Spring Boot application on port 8080.
cd smartstock
./mvnw spring-boot:run
3

Launch the React Frontend

Install Node dependencies and start the Vite dev server. The dashboard connects to Spring Boot to load products and run predictions.
cd frontend/frontend-smartstock
npm install
npm run dev
4

Run Your First Prediction

With all three services running, open the dashboard, select a product, and click Ejecutar Predicción IA to get an AI-powered demand forecast.
The Python AI service must be running on port 8001 before starting Spring Boot, because Spring Boot calls it directly at http://127.0.0.1:8001/predict/smart-stock. See the Quickstart for full setup details.

Build docs developers (and LLMs) love

Get started for freeTalk to us