Hi, I'm Ahmad! I have a technical background and hold double major in chemical engineering and chemistry and a Masters in Energy Policy Analysis. I have worked for 3 years in engineering and data analytics roles as Energy Analyst and a Data Operations Associate as a solar software start up. I love finding the hidden value of data science, I have been mentoring 3 individuals break into data science at different levels in their career.
I had taken the time to complete several coursera courses in SQL and Python and I am using this repository to showcase my skills, share projects and track my progress.
In this section I will list data analytics projects briefly describing the technology stack used to solve cases.
Code: Marketing Strategy.ipynbDescription: The dataset contains 2976 records. There is a list of client types, revenue collected and marketing campaign spending. The marketing strategies that were used is email, flyer, phone, sales contant 1, 2, 3, 4 and 5. The project includes the following steps: data loading and quality check, data cleaning, additional features and engineering, Exploartory Data Analysis (EDA) and statisitical analysis, final recommendations.
Skills: data cleaning, data analysis, descriptive statistics, correlation analysis, data visualization.
Technology: Python, Pandas, Numpy, Scipy Stats, Seaborn, Matplotlib.
Results: The creation of a multi-variable correlation chart for each of the client types for their marketing strategy. Using this, the marketing team can target clients based on their types more strategically without wasting budget. Code: Sales Analysis.ipynb
Description: The dataset contains 186850 records. The dataset has the order_id, product, quantity, price per item, date and address. The project includes the following steps: data loading and quality check, data cleaning, additional features and engineering, Exploartory Data Analysis (EDA) and answering business questions.
Skills: Data cleaning, data analysis, business analysis, data visualization.
Technology: Python, Pandas, Numpy, Seaborn, Matplotlib.
Results: Several questions have been answered for the sales team, this includes best sales months, cities with most products sold, time to display ads for boosting customer attraction, bulk sales analysis and most products sold. Dashboard: Maven_Pizza_Dashboard.pdf
Description: This was a Maven Analytics Challenge for November 2022. The dataset contains 5 tables. The data avalaible was regarding customer orders, number of orders, types of pizzas sold, timings and dates. The project includes the following steps: data loading and quality check, data cleaning, additional features and engineering, Exploartory Data Analysis (EDA) final recommendations.
Skills: Data cleaning, data analysis, business analysis, DAX, data visualization.
Technology: PowerBI, SQL, Python, Pandas, Numpy, Matplotlib
Results: A Dashboard showcasing to the customer ( Maven Pizzaria ) their KPIs and trends. The dashboard proposed several recommendations which included changing operational time of the store to lower cost, increase seating capacity as seating order is maxed, and offering discounted items/promotional deals. Dashboard:Boston Crime Rate Dashboard.pdf
Description: The dataset was obtained by merging crime statistics from the government of boston website between 2018 and 2022, with 305596 records. The information avalaible included crime ID, type of crime, district, date, time, and location. The project includes the following steps: data loading and quality check, data cleaning, additional features and engineering, Exploartory Data Analysis (EDA).
Skills: Data cleaning, data analysis, DAX, data visualization.
Technology:PowerBI, SQL, Python, Pandas, Numpy, Matplotlib
Results: I generated an interactive dashboard showcasing crime rate in different districts across different years. The dashboard also included crime rate trends, with highest crime rate in different districts with various timings, to help the Boston Government propose best solutions to combat crime in Boston. Dashboard 1: Sales Dashboard 1
Dashboard 2: Sales Dashboard 2
Description: The dataset contains vehicle sales in various countries. The data avalaible included order id, quantity, price, product, date, and address. The project includes the following steps: data loading and quality check, data cleaning, additional features and engineering, Exploartory Data Analysis (EDA) final recommendations.
Skills: Data cleaning, data analysis, business analysis, DAX, data visualization.
Technology: Tableau, SQL, Python, Pandas, Numpy
Results: A Dashboard showcasing to the customer their KPIs and trends over the past year.