dimmas_portfolio

Analytics Portfolio

Project 1: Munchys Supply Chain

• Objective: Develop an executive dashboard to monitor and analyze sales performance of Munchy’s Pet Supply.

• Goal: Provide key insights on revenue, product performance, customer segments, and regional sales to support data-driven decisions.

• Dataset: Sales transaction data including product categories, customer types, payment methods, regions, and sales metrics.

• Key Analysis:
  • Sales performance by region and customer segment
  • Top-performing products and categories
  • Revenue trends over time
  • Payment method distribution and impact
• Tools Used:
  • Excel – Data cleaning, preprocessing, and initial exploration
  • PostgreSQL – Data storage, querying, and transformation using SQL
  • Tableau – Data visualization and creation of interactive dashboards
• Outcome: Interactive dashboard enabling stakeholders to quickly assess sales trends, identify growth opportunities, and optimize business strategies.

Project 2: DataSearch Job Trends

• Objective: Develop a job market analytics dashboard to analyze job demand and hiring trends.
• Goal: Provide insights into job availability, industry demand, required skills, and job distribution to support career planning and workforce analysis.
• Dataset: Job listing data including job titles, industries, required skills, company names, locations, and posting counts.
• Key Analysis:
  • Top industries with the highest job demand
  • Most in-demand job roles and skills
  • Job distribution by location
  • Company-wise job posting analysis
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, querying, and transformation using SQL
  • Tableau – Interactive dashboard development and visualization
• Outcome: A dynamic dashboard that helps users understand job market trends, identify high-demand skills, and explore job opportunities across industries and locations.

Project 3: Just In Time Supply Chain

• Objective: Create a supply chain dashboard to analyze operational efficiency and logistics performance for JustinTime Supply Chain.

• Goal: Provide actionable insights on inventory management, supplier performance, delivery efficiency, and order fulfillment to optimize supply chain operations.

• Dataset: Supply chain data including order details, product categories, supplier performance, shipping status, delivery times, and fulfillment rates.

• Key Analysis:
  • Inventory levels and stock movement
  • On-time delivery rates and shipping performance
  • Supplier reliability and performance
  • Order fulfillment rates and bottleneck identification
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, SQL querying, and transformation
  • Tableau – Interactive dashboard creation and data visualization
• Outcome: A dynamic dashboard that helps stakeholders monitor supply chain health, improve delivery performance, optimize inventory, and enhance supplier management.

Project 4: Just In Time Shipment

• Objective: Develop a shipment dashboard to track delivery performance and shipping efficiency for JustinTime.

• Goal: Provide insights into shipment status, delivery timelines, shipping delays, and carrier performance to optimize logistics operations.

• Dataset: Shipment data including order IDs, shipping dates, delivery dates, shipment status, carrier details, and delivery performance metrics.

• Key Analysis:
  • On-time vs delayed shipments
  • Delivery status breakdown (on-time, late, in transit)
  • Carrier performance analysis
  • Shipment trends over time and delivery efficiency
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, SQL querying, and data transformation
  • Tableau – Dashboard creation and data visualization
• Outcome: A dynamic dashboard that enables stakeholders to monitor shipment performance, identify delivery issues, improve carrier management, and streamline logistics processes.

Project 5: Just In Time Inventory

• Objective: Create an inventory dashboard to monitor stock levels, product movement, and warehouse efficiency for JustinTime.

• Goal: Provide insights into inventory management, stock availability, turnover rates, and restocking needs to optimize supply chain operations.

• Dataset: Inventory data including product IDs, categories, stock levels, warehouse locations, reorder points, and stock movement history.

• Key Analysis:
  • Current stock levels by product and warehouse
  • Fast-moving vs slow-moving products
  • Inventory turnover rate analysis
  • Restock alerts and stockout identification
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, SQL querying, and data transformation
  • Tableau – Dashboard creation and data visualization
• Outcome: An interactive dashboard that helps stakeholders track stock levels, manage inventory efficiently, prevent stockouts, and optimize warehouse operations.

Project 6: Atlas Labs HR Dashboard

• Objective: Develop an HR dashboard to monitor workforce metrics and analyze employee-related data for Atlas Labs.

• Goal: Provide insights into employee demographics, turnover, hiring trends, and workforce distribution to support HR decision-making.

• Dataset: HR data including employee IDs, demographics, departments, job roles, tenure, hiring status, and attrition records.

• Key Analysis:
  • Employee distribution by department, role, and gender
  • Attrition rate analysis by department and job role
  • Hiring vs attrition trends over time
  • Workforce diversity and tenure distribution
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, SQL querying, and transformation
  • Tableau – Dashboard creation and data visualization
• Outcome: An interactive dashboard that helps HR teams monitor workforce trends, analyze attrition, track hiring needs, and support diversity and retention strategies.

Project 7: Databel Customer Churn

• Objective: Build a customer churn analysis dashboard to monitor customer retention and churn patterns for Databel.

• Goal: Provide insights into churn rates, customer behavior, and key factors influencing churn to support retention strategies.

• Dataset: Customer data including demographics, tenure, contract types, payment methods, service usage, and churn status.

• Key Analysis:
  • Churn rate by customer segment and contract type
  • Identification of key churn drivers (e.g., tenure, payment methods)
  • Customer distribution by churn status
  • Trends in active vs churned customers over time
• Tools Used:
  • Excel – Data cleaning and preparation
  • PostgreSQL – Data storage, SQL querying, and data transformation
  • Tableau – Dashboard creation and data visualization
• Outcome: An interactive dashboard that helps businesses understand churn patterns, identify at-risk customers, and implement data-driven customer retention strategies.

Project 8: Inventory Analysis for Acropolis Retail Ltd.

• Objective: Build an inventory analysis dashboard to track stock levels, product movement, and inventory performance.

• Goal: Provide insights into inventory health, stock availability, turnover rates, and replenishment needs to improve operational efficiency.

• Dataset: Inventory data including product IDs, categories, stock levels, sales data, reorder points, and warehouse locations.

• Key Analysis:
  • Stock levels by product and warehouse
  • Fast-moving vs slow-moving items
  • Inventory turnover rate and stock aging
  • Restocking needs and stockout risk identification
• Tools Used:
  • Excel – Data cleaning and preprocessing
  • PostgreSQL – Data storage, SQL querying, and data transformation
  • Tableau – Interactive dashboard creation and data visualization
• Outcome: A dynamic dashboard that enables stakeholders to monitor inventory status, optimize stock management, reduce stockouts, and improve supply chain efficiency.

Project 9: Divvy Historical Trip

• Objective: Develop a trip analysis dashboard to understand rider behavior and usage patterns for Divvy Bike Sharing.

• Goal: Provide insights into rider demographics, trip patterns, and differences between casual and member riders to support business strategies.

• Dataset: Divvy historical trip data including rider types, trip durations, start/end stations, rideable types, and trip dates.

• Key Analysis:
  • Rider segmentation: casual vs member riders
  • Trip duration and frequency analysis
  • Popular routes and stations
  • Ride patterns by day, month, and bike type
• Tools Used:
  • Excel – Data cleaning and preprocessing
  • PostgreSQL – Data storage, SQL querying, and transformation
  • Tableau – Interactive dashboard creation and data visualization
• Outcome: An interactive dashboard that helps stakeholders understand rider behavior, optimize bike distribution, improve service offerings, and enhance user experience.

Project 10: HealthStat Length of Stay (LOS) Comparison

• Objective: Create a Length of Stay (LOS) dashboard to analyze patient stay duration and hospital performance.

• Goal: Provide insights into average LOS, patient flow, and departmental efficiency to support healthcare management and operational improvements.

• Dataset: Hospital data including patient IDs, admission/discharge dates, departments, diagnoses, and length of stay records.

• Key Analysis:
  • Average LOS by department and diagnosis
  • LOS comparison across departments
  • Patient admission and discharge trends
  • Identification of departments with high or low LOS
• Tools Used:
  • Excel – Data cleaning and preprocessing
  • PostgreSQL – Data storage, SQL querying, and data transformation
  • Tableau – Dashboard development and data visualization
• Outcome: An interactive dashboard that enables healthcare providers to monitor patient LOS, optimize resource allocation, improve patient flow, and enhance operational efficiency.

Project 11: Analyzing Unicorn Companies

• Objective: Support an investment firm in analyzing high-growth company trends.
• Goal: Identify top-performing industries by company valuation and track the emergence rate of high-value companies.
• Dataset: Company information, valuations, industry classifications, and founding years.
• Key Analysis: Identified top unicorn-producing industries (2019-2021), peak year for new unicorns, and average valuation differences across industries.
• Tools: SQL (PostgreSQL), with data querying, aggregation, and trend analysis techniques.
• Outcome: Deliver insights to guide portfolio optimization and strategic investment decisions based on industry growth patterns.

Project 12: Evaluate a Manufacturing Process

• Objective: Enhance manufacturing quality through Statistical Process Control (SPC).
• Goal: Identify and minimize defects by establishing control limits and analyzing production data.
• Dataset: manufacturing_parts table, containing item_no, length, width, height, and operator data.
• Key Analysis: Calculated Upper/Lower Control Limits (UCL/LCL) for product height; identified out-of-control parts and operator performance.
• Tools used: SQL (PostgreSQL) for data analysis and SPC calculations.
• Outcome: Found 57 out of 363 parts out of control, with Operator 5 having the most alerts, leading to recommendations for root cause analysis and training.

Project 13: Analyzing Motorcycle Part Sales

• Objective: Analyze motorcycle part sales data to understand wholesale revenue by product line, month, and warehouse.
• Goal: Calculate net wholesale revenue for each product line, categorized by month and warehouse.
• Dataset: sales table, including order_number, date, warehouse, client_type, product_line, quantity, unit_price, total, payment, and payment_fee, covering June-August 2021 orders.
• Key Analysis: Determined top-earning wholesale product lines, compared revenue across three warehouses (North, Central, West), and identified monthly revenue trends.
• Tools used: SQL (PostgreSQL) for querying and aggregating sales data.
• Outcome: Engine Parts and Frame & Body were top revenue generators; Central Warehouse led in revenue; and revenue showed a strong upward trend from June to August.

Project 14: Impact Analysis of GoodThought NGO Initiatives

• Objective: Optimize GoodThought NGO’s impact and resource allocation using data from their PostgreSQL database (2010-2023).
• Goal: Analyze trends, evaluate program effectiveness, and identify improvement opportunities for the NGO.
• Dataset: GoodThought’s PostgreSQL database, containing Assignments, Donations, and Donors tables (2010-2023).
• Key Analysis: Identifying top-funded assignments, donor contributions by region/category, and high-impact assignments across regions.
• Tools used: SQL (PostgreSQL) for trend analysis.
• Outcome: Identified top-funded assignments, regional donor patterns, and high-impact assignments.

Project 15: Factors that Fuel Student Performance

• Objective: Explore factors influencing student success through analyzing lifestyle habits and exam performance.
• Goal: Uncover relationships between student habits and academic performance for educational improvement.
• Dataset: student_performance.
• Key Analysis: Examined correlations between study hours, extracurriculars, sleep duration, and exam scores/ranks.
• Tools used: SQL (PostgreSQL) for enabling the analysis of factors influencing student success.
• Outcome: Found positive links between increased study/extracurriculars and scores, optimal study hours (11-15 hrs), and balanced sleep (6-8 hrs) among top performers.

Project 16: Analyze International Debt Statistics

• Objective: Uncover key insights into the debt situation of developing nations, including identifying major debtors, debt distribution, and overall trends.
• Goal: Provide a clearer understanding of how debt supports economic development and offer valuable insights for stakeholders and policymakers.
• Dataset: International debt data collected by The World Bank.
• Key Analysis: Analyzed international debt data to identify the largest debtors, understand debt distribution, and recognize overall debt trends among 124 developing countries.
• Tools used: PostgreSQL was used to store and manage The World Bank’s international debt data for analysis and querying.
• Outcome: Identified 124 distinct developing countries in the dataset, with China having the highest total debt (approx. $285 billion USD) and Timor Leste having the lowest principal repayments (as low as $825,000 USD).

Project 17: When Was the Golden Era of Video Games?

• Objective: Explore if video games are improving over time or if their “golden age” has passed by analyzing review scores and global sales.
• Goal: Uncover the most celebrated eras in gaming history and gain insights into the business dynamics of successful games.
• Dataset: Data on video game critic scores, user ratings, and sales for the top 400 games released since 1977.
• Key Analysis: Analyzed video game data to determine if games are improving over time, identifying best-selling games and the years with the highest critic and user scores.
• Tools used: PostgreSQL (used for storing, managing, and querying the video game sales and review dataset).
• Outcome: Top-selling games were mostly from the late 2000s-2010s; 1998, 2002, and 2004 had the highest average critic scores, with 1998 being the top year.

Project 18: Analyzing Electric Vehicle Charging Habits

• Objective: Analyze electric vehicle (EV) charging usage data to help apartment building managers understand tenant charging habits.
• Goal: Provide insights into peak usage times, station availability, and demand patterns for better infrastructure planning and tenant satisfaction.
• Dataset: EV charging usage data from Kaggle, loaded into a charging_sessions table.
• Key Analysis: Analyzed EV charging usage data to understand tenant charging habits, identifying peak usage times, station availability issues, and overall demand patterns.
• Tools used: PostgreSQL (used for storing the charging_sessions dataset and performing queries for analysis).
• Outcome: Garage BI2 had the most unique users; popular charging times were Sundays between 3 p.m. and 7 p.m.; users “Share-9” and “Share-17” had significantly long average charging durations.

Project 19: Analyzing Industry Carbon Emissions

• Objective: Analyze industry carbon emissions to identify the worst-offending industries in 2017 based on product carbon footprints (PCFs).
• Goal: Calculate and compare total carbon footprints across different industry groups using publicly available data.
• Dataset: Product carbon footprints (PCFs) data from nature.com, stored in the product_emissions table.
• Key Analysis: Analyzed industry carbon emissions, specifically identifying the “Materials” industry group as the worst offender in 2017 with a total carbon footprint of 107,129 kgCO2.
• Tools used: PostgreSQL (used for storing and querying the product_emissions dataset to calculate and compare carbon footprints).
• Outcome: The “Materials” industry group had the highest total carbon footprint in 2017, amounting to 107,129 kgCO2.