hashijk/analyzing-nyse-data-project

This repository is aimed to document my New York Stock Exchange Analyzing Project, which is a final project of the first course of the Business Analytics Nanodegree provided by Udacity.

Project Description
This is a final project of the Introduction to data Course, which is one of the Business Analytics' Courses. In this project, you must prepare and analyze the data, and sharing the findings as a presentation that explaining the most important insights. I spent almost 5 days on this project, it was useful and challenging.

Getting Dataset
You can get the entire dataset via Kaggle platform. In this project I used the fundamentals.csv file as a smaller subset of the data.

Project Requirements
For the final project, I conducted three Tasks:
1. Complete my own data analysis and create a presentation to share your findings.
2. Develop a dashboard for a Profit and Loss Statement.
3. Create a Financial Forecasting Model using three scenarios.
Each of them has a detail, as following:

Task 1 Details
In this task, I framed three questions, and analyzing the data to get answers about them. These questions included quantitative variables such as [financial metrics] and qualitative variables such as [GICS Sector or GICS Sub Industry]. I used a descriptive analysis of these questions, like [calculating means, std, quartiles, etc.]. And using these metrics to extracting the insights and interpreting them from a financial perspective.

Task 2 Details
This task is more advanced than the last, here I build a Dynamic P&L Statement that shows all the financial years for each a company and which the GICS Sectoer and the Sub Industry is located. The outcomes of this task are [drop-down list that shows the 500 companies] and the P&L metrics like [Total Revenue, COGS, Gross Profit, etc.]**.

Task 3 Details
In this last task, I created a financial model for all the company, that forecasts out the Gross Profit, Operating Profit, or EBIT for two more years using three scenarios (Best case, Weak case, and Base case). This financail model was dynamic, so it will change for every company and every scenario case. I used offset, index, match and lookup functions to do this dynamic model. And I uesd the moving averages mothed to forcast the next two years for each company.

Project Methodology
To do these complex and long process we need to build a methodology to be as a plan of doing these process. My methodology was smilliar to the Data Science Methodology, and it contains these phases:
1. Understanding the data.
2. Selecting the data.
3. Cleaning the data.
4. Preparing the data.
5. Analyzing the data.
6. Sharing the findings to others.

Phase 1: Understanding the data One of the most important points in dealing with data is this step. You can't group your data in a good level of granulatiy without imaging how your data shaped. In this project, I typed in 2 questions that's made me understand the data well. These questions are 1. What is the level of granulatiy? 2. What does mean each column?. By answering them, you will get a clear idea about the data.

Phase 2: Selecting the data Some situations the first point you do, is selecting the data then cleaning the data. But in some situations the proper behavior is cleaning the dat then selecting the data. There a lot talking here, but it isn't our scope. Hence, I selected the IT Sub Industry data to analyze it.

Phase 3: Cleaning the data The data was cleaned, you just need to chane the names of columns to be more understandable.

Phase 4: Preparing the data This part of project was the largest part in the project in terms of spending the time, there are 12 sheets in a project workbook, nine of them are specialists in preparing the data purposes. I used a lot of Pivot Tables to sum the data well. Then aggregating the final data in a one sheet, then use this data to the analyzing purposes.

Phase 5: Analyzing the data This part is specialists to analyze the data. The first type of analyzing is the descriptive analysis, then build a dynamic P&L dashboard, then build a financial Model to forecast the next two years for each company.

Phase 6: Sharing the findings to others In this part, I created a simple presentation that concise and convey all the questions' answers which related to the descriptive analysis. And sharing a copy of sheets that contain the P&L Statement and the financial model dashboard.

Project Outcomes

1. IT Sub Industry Summary Statistics.
   
2. Dynamic P&L Statement for 500 companies.
   
3. Dynamic Forecasting Financial Model.
   

That is all for now.