Point72 Interview Questions

In a dice game, you roll a fair six-sided die once. After seeing the result, you may choose to either accept the result or roll the die a second time. What is the expected value of the result if you play optimally?

What is the difference between deep Q-learning and Q-learning?

You roll a 100-sided die and bet on a number; if you guess correctly, you win an amount equal to the number you bet on. What is your optimal betting strategy?

How would you calculate a covariance matrix when the underlying data is too large to fit into memory?

In the secretary problem, given n independent and identically distributed random variables drawn from a uniform distribution, what is the optimal strategy to maximize the expected return when you can only select the first variable that meets your criteria? Describe the method for finding this strategy.

What is the time and space complexity of finding the most profitable buy and sell dates given stock price data, if you are allowed only one buying and one selling transaction?

What happens to the F-statistic and t-statistic if you replicate the data in a dataset?

Explain bias and variance. Which models tend to have higher bias versus higher variance?

Can a tuple or a list be used as a key in a dictionary?

What are the assumptions required for linear regression?

How much should you be willing to pay to play the following game? You start with $1. You flip a fair coin. If it lands on heads, you double your winnings and flip again. If it lands on tails, the game is over and you collect the money you've won. You continue playing until you land on tails.

How would you create a predictive model of y given x, where x is a continuous variable between 0 and 10 and is linear on the integers? Follow-up: If you model this using 10 separate regressions, what would be the effect? If you average the regressions at the integers, would these be biased estimates?

What are the assumptions of linear regression?

Can you explain logistic regression to someone who is not familiar with it?

Given a table containing names and ages with some duplicate entries, how would you return all duplicate rows using SQL?

Design and implement a low-latency trading system that incorporates order latency as a parameter for backtesting strategies.

What is the event loop?

How do the estimated beta coefficients and t-statistics change in Ordinary Least Squares (OLS) regression if each sample in the dataset is duplicated?

A college maintains department information in one table and student information in another table. Write a SQL query to display the number of students by major in descending order.

Given an array of dates in string format (e.g., '20050301'), write a function that returns the year and quarter for each date (e.g., '20050301' => '2005Q1').

How would you remove an element from a linked list using an iterator?

Given an array of integers, find the contiguous subarray with the largest sum and return the sum.

What are the assumptions of linear regression, and what are the differences between linear regression and logistic regression?