Project Title

Restaurant Demand Pressure Analysis - Lisbon (2023–2024)

---

📌 Project Overview

This project analyzes city-level demand pressure affecting restaurants in Lisbon using public, real-world data.
Instead of relying on confidential restaurant sales data, the project builds a Demand Pressure Index (DPI) using external signals such as tourism, weather, and calendar effects.

The goal is to show when demand peaks occur, why they happen, and which restaurants are most exposed, supporting better operational and workforce planning decisions.

---

🎯 Key Questions Answered

• What does restaurant demand pressure look like over time in Lisbon?
• Why does demand increase on certain days or periods?
• Who (which restaurants) is most exposed to city-level demand peaks?

---

🧠 Methodology (High Level)

1. Data Collection

   • Hotel occupancy rates (tourism proxy)
   • Weather data (temperature, conditions)
   • Calendar data (weekends, public holidays)
   • Restaurant metadata (ratings, popularity, cuisine)

2. Data Processing

   • Data cleaning and normalization in Python
   • Calendar and seasonal feature engineering
   • Aggregation at daily and monthly levels

3. Demand Pressure Index (DPI)

   • Composite indicator representing city-wide demand intensity
   • Normalized and comparable across time

4. Restaurant Exposure Analysis

   • Combines city demand pressure with restaurant popularity
   • Identifies restaurants most sensitive to demand peaks

5. Visualization

   • Interactive dashboards built in Tableau
   • Executive-friendly insights for decision-making

---

📊 Dashboards

The project includes three main dashboards:

1. City Demand Overview
   Seasonality, trends, and peak demand periods https://public.tableau.com/app/profile/rui.braz/viz/LisbonDemandOverview/LisbonDemandOverview?publish=yes

2. Demand Drivers Analysis
   Relationship between demand, tourism, weather, and holidays https://public.tableau.com/app/profile/rui.braz/viz/SeasonalityandExternalDemandDrivers/SeasonalityDemandDrivers?publish=yes

3. Restaurant Exposure Analysis
   Identification of highly exposed restaurants during peak demand https://public.tableau.com/app/profile/rui.braz/viz/RestaurantExposurevsCityDemandPressureLisbon/RestaurantExposure?publish=yes

---

🛠️ Tools & Technologies

• Python (Pandas, NumPy)
• SQL / MySQL
• Tableau
• Public open datasets (municipal and tourism data)

---

👥 Who This Project Is For

• HR & Workforce Planning Analysts
• Operations & Business Analysts
• Hospitality & Urban Analytics stakeholders

The approach is transferable to any context where staffing and capacity depend on external demand drivers.