1

Market Data Assignment
MFIT 841: Digital Capital Markets
Overview
This is going to be hard. The data are large and confusing. Your job is to find a way to distill the
important information into a simple and straightforward analysis. Good luck!
Direction
Students will analyze two datasets that include quotes and trades. Your job will be to:
1)
2)
3) Merge the quotes and trades datasets by symbol and datetime
4) Calculate bid-ask spreads, effective spreads, trading volume, minute-to-minute returns,
volatility of minute-to-minute returns and any other variable that you think is important to
describe market quality.
Answer the following questions:
- Are these stocks liquid or illiquid?
- Are all stocks the same?
- Why is the effective spread different than the bid-ask spread?
- Are these deep markets?
- Are spreads and depth correlated?
-
- Can you predict future price movements using only this data?

You are going to have to dig deep, Google a lot and figure out how to analyse this data. I
recommend using R or Python. Here are some resources that I use:
1) Install and initial steps to use a data science package:
a. R and R Studio: https://towardsdatascience.com/how-to-install-r-and-rstudio-
584eeefb1a41
b. https://www.codecademy.com/articles/install-python-data-analysis
2) Import with:
a. R - https://www.datacamp.com/community/tutorials/r-data-import-tutorial
b. Python - https://towardsdatascience.com/how-to-read-csv-file-using-pandas-
ab1f5e7e7b58
3) Lots of initial code in both Python and R by searching here: https://stackoverflow.com
4) Manual for the quotes and trades dataset are included. You do not have all of the data, I
only included the most relevant fields.


2

The report should be no longer than 5 pages double spaced with 12-point font. This includes
tables, figures, references, and links. Writing for financial professionals requires very compact
Describe the data

- How many symbols
- Averages, sums, distributions
- Tell me what the data is telling you

5
Analysis

-
- Are these variables correlated
- Are the markets liquid
- Are all symbols comparable?
- Can you predict or explain the dynamics of the data?
- Tell me what you have and can learn from the data


10
Professional Quality of Case write-up

- Double spaced, 12 pt. font and 5 pages maximum
- Free of grammar and spelling errors
- Clear and concise presentation of ideas and analysis


5
TOTAL 20