In the late 1990s, getting in on the right Initial Public Offering (IPO) was like winning the lottery. First-day returns for some technology companies were many times their initial offering price, and if you were lucky enough to get in on an allocation, you were in for a windfall. Here are a few of the top first-day performers from the period:
- VA Linux up 697%, 12/09/99
- Globe.com up 606%, 11/13/98
- Foundry Networks up 525%, 9/28/99
While the days of dotcom mania are far behind us, IPOs can still have outsized first-day returns. Here are just a few that rose substantially on their first day of trading in the past year:
- Bloom Energy up 67%
- Pinduoduo up 32%
- Tenable up 32%
As you can see, this is still a market worth paying attention to. In this chapter, we'll take a closer look at the IPO market. We'll see how we can use machine learning to help us decide which IPOs are worth a closer look and which ones we may want to take a pass on.
Here's what we'll cover in this chapter:
- The IPO market
- Data cleansing and feature engineering
- Binary classification with logistic regression
- Model evaluation
- Feature importance