Quantitative Finance Research Training

Distinguish the ownership, lending, pooled-investment, and contingent-payoff roles of stocks, bonds, ETFs, futures, and options.

Given bid and ask quotes and an execution objective, calculate the spread, choose between a market and limit order, and identify the principal risk of that choice.

Use open, high, low, close, adjusted-close, volume, and corporate-action records to determine whether a price discontinuity represents a market move or an adjustment.

Import market observations from a CSV file into a pandas DataFrame and inspect its columns, index, data types, and summary information.

Parse dates, construct a sorted DatetimeIndex, select a date range, and align two market series on shared dates.

Detect and resolve missing values, duplicate timestamps, and nonnumeric observations according to a stated data policy.

Plot a labeled price series and use the chart to flag gaps, extreme observations, and suspicious discontinuities for investigation.

Convert among fractions, decimals, percentages, and basis points, and calculate a percentage change.

Solve or rearrange a one-variable equation used in a financial calculation.

Calculate simple returns from a price series and construct the corresponding compounded wealth index in Python.

Calculate log returns and verify their additivity across consecutive periods.

Convert a nominal interest rate into an effective rate for a stated compounding frequency.

Calculate the present value of one or more dated cash flows using a discount rate expressed in matching period units.

Distinguish a population, sample, parameter, and sample statistic in a market-research scenario.

Calculate and interpret the mean, median, quantiles, and interquartile range of a return sample.

Calculate and interpret sample variance and sample standard deviation.

Use a histogram to identify skewness, heavy tails, and potential outliers in observed returns.

Estimate the probability of a stated market event from empirical frequency and describe the estimate's data limitations.

Calculate and interpret covariance and correlation for two date-aligned return series.

Construct and interpret a bootstrap confidence interval for a sample mean, and assess its economic significance separately from its statistical uncertainty.

Specify a falsifiable strategy-research protocol containing a signal, decision rule, holding period, benchmark, cost assumption, and rejection criterion.

Diagnose look-ahead bias and survivorship bias in short research scenarios and state how each design should be corrected.

Create chronological development and final-test periods while keeping the final test period untouched during model selection.

Maintain a log of attempted signal variants and use it to explain the data-snooping and multiple-testing risk in a reported result.

Compare return distributions, volatility, and drawdowns during an ordinary period and a preidentified shock such as the 2008 financial crisis or 2020 COVID-19 crash.

Calculate a moving-average signal using only prices available at each signal date.

Convert a signal into constrained long-or-flat target positions and lag the positions so simulated trades use no future information.

Calculate gross strategy returns and compare them with a passive benchmark over identical dates.

Calculate strategy turnover and deduct proportional transaction costs to obtain net returns.

Construct an equity curve and calculate its running drawdown and maximum drawdown.

Calculate annualized return, annualized volatility, and the Sharpe ratio on held-out data using stated frequency and risk-free-rate assumptions.

Verify long-only portfolio constraints and calculate portfolio returns as weighted sums of constituent returns.

Calculate two-asset portfolio variance and explain how changing correlation alters diversification while constituent risks remain fixed.

Construct and compare equal-weighted and inverse-volatility portfolios using only estimates available before each rebalance date.

Apply a calendar rebalancing rule and calculate turnover and net performance after rebalancing costs.

Stress-test a portfolio over the 2020 equity crash and the 2022 stock–bond selloff and compare the failure modes revealed by the two events.

Create a research notebook with a frozen specification and separate sections for data, hypothesis, method, results, limitations, and conclusion.

Implement data-ingestion checks for date order, duplicate timestamps, missing values, and implausible returns, with explicit warnings or failures when a check is violated.

Implement an end-to-end pipeline that converts validated prices into a lagged signal, positions, benchmark returns, transaction-cost-adjusted strategy returns, and performance metrics.

Using only development data, test reasonable parameter and cost assumptions, freeze the selected specification, and then evaluate it once on the final test period and preidentified stress periods.

Re-run the complete notebook from raw input to final outputs and write a go, revise, or reject recommendation that separates evidence from speculation and names the principal failure modes.