search

yeyeyeye721 / Investor-Side-IRR

0 stars 0 forks source link

Pitchbook (whether investors' expectations are correct) #2

Open MingyangZhang1995 opened 2 years ago

MingyangZhang1995 commented 2 years ago

Goal: Check whether investors' expectations are correct or not. Calculate the correlation between company charateristics (before 2020/07) and their recent performance (2020/07-2021/09)

company 2020/07 raised funding | 2020/07-2021/09 performance Step1: (X) company characteristics before 2020/07 employee, funding team, revenue, etc.

Step2: (Y) company 2020/07-2021/09 performance: IPO, M&A, Failure*** (website), Raise extra funding

Step3: fixed effect model reg Y X i. industry

MingyangZhang1995 commented 2 years ago

Step1: (X) company characteristics before 2020/07 employee, funding team, revenue, etc.

Besides the variables in table "Company" and "CompanyIndustryRelation", I currently got the following variable:

  1. Female_Exec: the number of current female executive in a company. This variable calculated by merging "Company", "CompanyExecRelation" and "Person" where the "IsCurrent" column equals to "Yes".

  2. Male_Exec: the number of current male executive in a company. (Similar to Female_Exec)

  3. PhD_count: the number of current executive with a PhD in a company. This variable calculated by merging "Company", "CompanyExecRelation" and "Person" where the "Education" is like "%Ph.D%" or "%Doctor%", the "IsCurrent" column equals to "Yes".

  4. MAMBA_count: the number of current executive with a MA or MBA degree but without a PhD in a company. This variable calculated by merging "Company", "CompanyExecRelation" and "Person" where the "Education" is not like "%Ph.D%" and "%Doctor%", but like "%Master%" or "%MBA%", the "IsCurrent" column equals to "Yes".

yeyeyeye721 commented 2 years ago
  1. gender
  2. race (last name)
  3. ESG (survey report)

Founder characteristics:

  1. Ivy League
  2. Serial Founder
  3. Number of founders
  4. US company
  5. Number of Employees
  6. Revenue/ positive revenue
  7. Compnay age, founding date
  8. B2B
  9. Focus on Domestic market
yeyeyeye721 commented 2 years ago

Company ID Company Name Pre-characteristics Post-performance

MingyangZhang1995 commented 2 years ago

Question: Some records of "PrimaryCompany" in table "Person" consist of a company name and a "(Former)" following it. What does the (Former) mean? e.g. Jack is the founder of the company, does (Former) mean that he was the Founder but left the company. Do we consider these records?

MingyangZhang1995 commented 2 years ago

Currently got factors ((Former) took into account):

  1. BusinessStatus: indicates whether the company generating revenue.
  2. Employees: number of employees
  3. YearFounded
  4. PrimaryIndustrySector: Except for the information of industry, some of the values have a (B2B) or a (B2C) in the end, so it might be useful?
  5. HQCountry: indicates the Head Quarter location of the company, therefore indicating whether it is a US company.
  6. Revenue: exact value of revenue, but many missing values.
  7. Api_Founder: number of founders with the race of asia/pacific.
  8. Black_Founder: number of founders with the race of black
  9. Hispanic_Founder: number of founders with the race of hispanic.
  10. White_Founder: number of founders with the race of white.
  11. Female_Founder: number of Female founders.
  12. Male_Founder: number of male founders.
  13. Ivy_League_Founder: number of founders graduated from ivy league. Race is predicted by the Python package ethnicolr founction pred_census_ln([DataFrame], [Column_Name], 2010) Founder means the PrimaryPosition is like "%Founder%"
MingyangZhang1995 commented 2 years ago

There are 22085 (out of 32832) companyID in CompanyCharacteristics2020 do not exist in 2021 Company table. However, these missing records do not mean bankrupt. For example, the website of "100019-08" is http://uoko.com/, which can be entered successfully.