Retail-Analytics-TimeSeries-EDA

An advanced Exploratory Data Analysis (EDA) and Time-Series Forecasting project analyzing Adidas retail sales patterns across multiple regions to discover seasonality and revenue trends.

Un proyecto avanzado de Análisis Exploratorio de Datos (EDA) y Pronóstico de Series de Tiempo que analiza los patrones de ventas minoristas de Adidas en múltiples regiones para descubrir su estacionalidad y tendencias.

---

The Challenge / El Desafio

To analyze a massive retail dataset containing daily sales from thousands of stores. We identify key performance indicators (KPIs), autocorrelation loops, and seasonal spikes to optimize inventory planning.

Analizar un dataset masivo de retail de miles de tiendas. Identificamos KPIs, ciclos de autocorrelación y picos estacionales para optimizar la planificación del inventario de ropa deportiva.

Tech Stack / Tecnologias Usadas

• Language: Python 3.10+
• Exploratory Data Analysis: pandas, numpy
• Visualization Dashboards: plotly, seabon, matplotlib
• Stats: Autocorrelation (ACF) and Partial Autocorrelation (PACF) testing.

Key Insights / Hallazgos Clave

• Q4 Spikes: Consistent revenue increases during the final quarter of the year.
• Product Margins: Certain footwear lines provide disproportionate operating profit compared to apparel.

How to Run / Instalacion

# Clone
git clone https://github.com/JulianDataScienceExplorerV2/Retail-Analytics-TimeSeries-EDA.git
cd Retail-Analytics-TimeSeries-EDA

# Install
pip install pandas plotly matplotlib numpy

# Run the visualizer scripts
python Visualizacion_Adidas/Visualizacion_Adidas_QRevenue.py

---

Julian David Urrego Lancheros
Data Analyst & Marketing Science