Quant interview questions
1,322 questions in the style trading and research firms ask, from probability and brainteasers to options, statistics and coding. Every question is open to read; the 50 in the free sample show their worked solutions here.
378 questions · page 9 of 10 · Clear filters
- You join trades to quotes using the exchange timestamp on both. What can still go wrong?Research case studies · Advanced
- How many independent observations are needed to detect an information…Research case studies · Advanced
- Your model degrades sharply after a known market structure change.Research case studies · Advanced
- Treatment A succeeds in 81/87 small cases and 192/263 large ones; treatment B…Research case studies · Advanced
- You want the effect of advertising spend on sales and propose regional weather…Research case studies · Advanced
- Successive trade-price changes have autocovariance −0.0004 (in dollars squared).Research case studies · Advanced
- Daily true variance is (1%)².Research case studies · Advanced
- Using daily closing prices, you find that large-cap returns predict next-day…Research case studies · Advanced
- A Fermi estimate multiplies four independent factors, each uncertain to within…Research case studies · Advanced
- Strassen’s matrix multiplication satisfies T(n) = 7T(n/2)+O(n²).Data structures and algorithms · Advanced
- You add an array of shape (100, 5) to one of shape (5,). What happens?Python and data for quants · Foundation
- What is sum([i * j for i in range(3) for j in range(3) if i != j])?Python and data for quants · Foundation
- How many elements does the result of adding NumPy arrays of shapes (3, 1) and (1, 4) have?Python and data for quants · Foundation
- What is the length of np.arange(10).reshape(2, 5).sum(axis=0)?Python and data for quants · Foundation
- What does pd.Series([1, None, 3]).mean() return?Python and data for quants · Foundation
- For prices 100,110,99, what is the last value of pct_change()?Python and data for quants · Foundation
- A Series has 10 values. How many non-missing values does s.rolling(3).mean() contain?Python and data for quants · Foundation
- The New York equity open is 9:30 local time.Python and data for quants · Foundation
- A strategy grows $100 to $150 over three years.Python and data for quants · Foundation
- A strategy wins 40% of trades with an average gain of 3 and loses 60% with an…Python and data for quants · Foundation
- You test x in container millions of times against a fixed collection of 100,000 ids.Python and data for quants · Foundation
- A backtest computes pnl = signal * returns, where both are indexed by day. What is wrong?Python and data for quants · Applied · Free solution
- You need the quote in force at the instant of each trade. Which join?Python and data for quants · Applied · Free solution
- A strategy has a daily Sharpe ratio of 0.1. What is its annualised Sharpe ratio?Python and data for quants · Applied
- Your gross Sharpe ratio is 2 and your net Sharpe ratio is 0.1.Python and data for quants · Applied
- You compute a feature with df.rolling(21, center=True).mean().Python and data for quants · Applied
- Roughly how much memory does a list of ten million distinct Python integers…Python and data for quants · Applied
- You add two pandas Series with partly different indexes. What do you get?Python and data for quants · Applied
- What does [f() for f in [lambda: i for i in range(3)]] evaluate to?Python and data for quants · Applied
- What does round(2.5) return in Python 3?Python and data for quants · Applied
- What is the value in np.array([127], dtype=np.int8) + 1?Python and data for quants · Applied
- You take b = a[[0, 2, 4]] from a NumPy array a and then set b[0] = 99. What happens to a?Python and data for quants · Applied
- For the data 1,2,3,4, pandas’ Series.std() (default ddof=1) returns what, to…Python and data for quants · Applied
- A daily signal is computed from each day’s close.Python and data for quants · Applied
- Prices go 100 → 110 → 99. What is the total log return, to five decimals?Python and data for quants · Applied
- Portfolio weights move from (0.5,0.5) to (0.7,0.3). What is the one-way turnover?Python and data for quants · Applied
- A feature is standardised by subtracting its mean and dividing by its standard…Python and data for quants · Advanced
- You build a ten-year backtest on the stocks currently in an index.Python and data for quants · Advanced
- Estimate ∫₀¹x² dx with the trapezoid rule on two equal intervals.Numerical methods · Foundation
- For [[4, 1], [1, 3]]x = [1, 2], one Jacobi iteration from x = (0,0) gives what…Numerical methods · Foundation