Reference

Quantitative finance glossary

Definitions used across the Insights library. Entries with a full treatment link to a dedicated article containing the mathematics, interpretation, and practical limitations.

Quick index

Active share: One half of the sum of absolute portfolio-weight differences from a benchmark.
Alpha factor: A measurable security characteristic or signal used to forecast relative future returns.
Beta neutral: A portfolio construction target in which estimated market beta is approximately zero.
Capacity: The amount of capital a strategy can deploy before market impact, liquidity, or crowding materially reduces its expected performance.
Cross-sectional ranking: Ordering securities against one another at the same observation time using a signal or characteristic.
Dollar neutral: A portfolio whose long and short base-currency notionals offset, producing approximately zero net notional exposure.
Expected return: The return estimate used by an allocation model. It is an uncertain model input, not a guaranteed outcome.
Factor exposure: The sensitivity of a security or portfolio to a specified factor, estimated from holdings, characteristics, or a return model.
Factor timing: The deliberate variation of factor exposure through time using forecasts of factor performance or risk.
Implementation shortfall: The performance difference between a paper portfolio at the decision price and the realized executed portfolio.
Information coefficient (IC): The cross-sectional correlation between a signal score and a subsequent return. Rank IC uses ranked values and measures whether the signal orders securities correctly.
Maximum drawdown: The largest peak-to-trough decline in a cumulative return or portfolio-value series.
Portfolio optimization: The selection of portfolio weights to maximize or minimize a stated objective subject to constraints.
Risk budget: A limit or allocation assigned to a source of portfolio risk, such as an asset, strategy, or factor.
Rolling ICIR: The mean information coefficient divided by its standard deviation over a trailing window, usually annualized. It measures the persistence of ranking skill rather than one period’s IC.
Sharpe ratio: Mean excess return divided by return volatility, expressed on a consistent time scale.
Slippage: The signed difference between an intended or reference execution price and the price actually achieved.
Sortino ratio: Mean return above a minimum acceptable return divided by downside deviation rather than total volatility.
Tracking error: The standard deviation of active return relative to a benchmark.
Turnover: The amount of portfolio trading required between two sets of weights, under a stated convention.
Universe selection: The point-in-time rules determining which securities are eligible for research or portfolio construction.

Currency and return convention

International portfolios require one reporting currency. Let b be the portfolio base currency, l the security's local currency, and $X_t^{b/l}$ the number of base-currency units paid for one unit of local currency. Unless a term states otherwise, a local asset return is translated as

$1+R_{t\rightarrow t+h}^{(b)}=(1+R_{t\rightarrow t+h}^{(l)})(1+R_{t\rightarrow t+h}^{b/l}).$

The quote direction, return horizon, sampling frequency, FX hedge, compounding convention, and annualization factor must be stated. Changing the base currency can change measured return, volatility, drawdown, and risk-adjusted ratios even when the local asset price is unchanged.

Formal reference

Formulas show a standard convention, not the only valid convention. A production calculation should record any departure explicitly.

Term	Definition and formula	Units and values	Interpretation and importance	Related terms
Active share	One half of the sum of absolute portfolio-weight differences from a benchmark. $\operatorname{AS}=\tfrac12\sum_i\|w_{p,i}-w_{B,i}\|$	Units and convention Dimensionless fraction or percentage of NAV. Values From 0 to 1 for standard fully invested long-only portfolios; it can exceed 1 with leverage or short positions.	Interpretation Zero means identical weights; larger values mean a greater holdings-level departure from the benchmark. Why it matters It measures portfolio difference directly and complements return-based tracking error.	Tracking error Turnover Factor exposure
Alpha factor	A measurable security characteristic or signal used to forecast relative future returns. $f_{i,t}=g(x_{i,t})$	Units and convention Input-specific before normalization; ranks, percentiles, and z-scores are dimensionless. Values Depends on construction. A z-score is unbounded; a percentile is usually in [0,1] or [0,100].	Interpretation The direction convention must state whether larger values predict larger or smaller subsequent returns. Why it matters Factor definition, timestamp, normalization, and universe determine what evidence a backtest actually evaluates.	Cross-sectional ranking Universe selection Factor exposure
Beta neutral	A portfolio construction target in which estimated market beta is approximately zero. $\beta_p=\sum_i w_i\beta_i\approx0$	Units and convention Dimensionless, provided asset and market returns use the same currency and return convention. Values Target is zero within a stated tolerance. Realized beta can move as holdings and covariances change.	Interpretation The portfolio is designed to have little first-order sensitivity to the specified market factor. Why it matters It helps distinguish security-selection return from broad market direction, but does not remove sector, currency, or nonlinear risk.	Factor exposure Dollar neutral Risk budget
Capacity	The amount of capital a strategy can deploy before market impact, liquidity, or crowding materially reduces its expected performance. $K^*=\sup\{K:\widehat\alpha_{net}(K)\geq\alpha_{min}\}$	Units and convention Capital in a declared base currency, such as USD, EUR, GBP, or JPY; sometimes reported as a range rather than a point estimate. Values Non-negative and model-dependent. There is no universal upper bound or invariant estimate.	Interpretation It is the deployable scale consistent with a stated net-performance or market-impact threshold. Why it matters A statistically attractive strategy may be economically unimportant if it cannot absorb meaningful capital.	Turnover Slippage Implementation shortfall
Cross-sectional ranking	Ordering securities against one another at the same observation time using a signal or characteristic. $q_{i,t}=(\operatorname{rank}(f_{i,t})-1)/(N_t-1),\quad N_t>1$	Units and convention Rank is an integer; the displayed percentile rank q is dimensionless. Values Ranks run from 1 to N_t and the displayed convention maps them to [0,1]. Other percentile conventions and ties must be stated.	Interpretation It describes relative position within the eligible universe, not the absolute economic magnitude of a signal. Why it matters Ranking reduces sensitivity to outliers, but results still depend on universe composition, tie handling, and direction.	Information coefficient (IC)Universe selection Alpha factor
Dollar neutral	A portfolio whose long and short base-currency notionals offset, producing approximately zero net notional exposure. $\sum_i N_i^{(b)}=0,\qquad N_i^{(b)}=N_i^{(l)}X_i^{b/l}$	Units and convention Notional in the portfolio base currency b; X^{b/l} is units of base currency per unit of local currency. Values Net notional targets zero within tolerance; gross notional remains positive and must be reported separately.	Interpretation Long and short market values offset after FX translation. The conventional name applies even when b is EUR, GBP, JPY, or another currency. Why it matters It controls net capital exposure but does not imply beta neutrality, factor neutrality, or FX-risk neutrality.	Beta neutral Factor exposure Turnover
Expected return	The return estimate used by an allocation model. It is an uncertain model input, not a guaranteed outcome. $\mu_{i,t}^{(b)}=\mathbb{E}_t[R_{i,t\rightarrow t+h}^{(b)}]$	Units and convention Return over horizon h or annualized return, in a declared base currency b. Arithmetic and log-return conventions are not interchangeable. Values A simple-return forecast is bounded below by −100% and unbounded above; model estimates may require clipping or shrinkage.	Interpretation It is a conditional estimate based on information available at t, not a realized return or promise. Why it matters Optimized weights can be highly sensitive to small differences in expected-return estimates.	Portfolio optimization Sharpe ratio Rolling ICIR
Factor exposure	The sensitivity of a security or portfolio to a specified factor, estimated from holdings, characteristics, or a return model. $R_{p,t}-R_{f,t}=\alpha+\beta_f F_t+\varepsilon_t$	Units and convention Regression beta is dimensionless when portfolio and factor returns use the same units; characteristic exposures retain their stated scale. Values Generally unbounded. Zero means neutral to the specified factor model, not risk-free.	Interpretation Positive and negative values describe the direction and magnitude of sensitivity under the chosen model. Why it matters Unintended exposures can make apparently different strategies respond to the same underlying risk.	Beta neutral Risk budget Alpha factor
Factor timing	The deliberate variation of factor exposure through time using forecasts of factor performance or risk. $w_{f,t}=g(z_t,\widehat\mu_{f,t},\widehat\Sigma_t)$	Units and convention Factor weights are fractions of capital or risk; predictors retain their declared units until normalized. Values Defined by the timing rule and exposure bounds; zero means the factor is omitted at that date.	Interpretation Exposure changes because the expected opportunity or risk is believed to vary through time. Why it matters Timing can adapt to regimes, but adds estimation error, turnover, and another layer of model-selection risk.	Rolling ICIR Expected return Turnover
Implementation shortfall	The performance difference between a paper portfolio at the decision price and the realized executed portfolio. $\operatorname{IS}=(V_{paper}^{(b)}-V_{realized}^{(b)})/NAV_0^{(b)}$	Units and convention Return, percentage, basis points, or base-currency amount. All legs and fees must be translated to the same base currency b. Values Signed; positive commonly denotes a cost. It can exceed the quoted spread because it includes delay, impact, fees, and missed trades.	Interpretation It measures the total economic gap between an investment decision and its implementation. Why it matters It is broader than slippage and is the relevant bridge from paper performance to realized performance.	Slippage Turnover Capacity
Information coefficient (IC)	The cross-sectional correlation between a signal score and a subsequent return. Rank IC uses ranked values and measures whether the signal orders securities correctly. $\operatorname{IC}_t=\operatorname{corr}_{\rm rank}(f_{i,t},R^{(b)}_{i,t\rightarrow t+h})$	Units and convention Dimensionless. Returns must use one horizon and one base currency b across the cross-section. Values From −1 to +1. Zero indicates no monotonic cross-sectional association.	Interpretation The sign gives ranking direction; magnitude gives the strength of association on one observation date. Why it matters It separates signal-ranking evidence from the realized performance of a particular portfolio construction.	Rolling ICIR Cross-sectional ranking Alpha factor
Maximum drawdown	The largest peak-to-trough decline in a cumulative return or portfolio-value series. $\operatorname{MDD}=\max_t\left(1-V_t/\max_{s\le t}V_s\right)$	Units and convention Dimensionless fraction or percentage of portfolio value in the reporting base currency. Values From 0 to 100% for a non-negative unlevered wealth series; leveraged strategies can lose more than initial capital.	Interpretation It reports the worst historical loss from a prior high before recovery, if any. Why it matters Drawdown captures path-dependent capital loss that volatility and Sharpe ratio can obscure.	Sharpe ratio Sortino ratio Tracking error
Portfolio optimization	The selection of portfolio weights to maximize or minimize a stated objective subject to constraints. $w^*=\arg\max_{w\in\mathcal W}{\mu^\mathsf{T}w-\tfrac{\lambda}{2}w^\mathsf{T}\Sigma w}$	Units and convention Weights are fractions of capital or gross notional. Every objective term must be placed on a consistent return and time scale. Values The feasible values are defined by the budget, bounds, leverage, liquidity, currency, and exposure constraints in the set W.	Interpretation The result is optimal only for the specified inputs, objective, constraints, and numerical method. Why it matters It turns forecasts and risk estimates into an explicit capital allocation while exposing the assumptions behind that decision.	Expected return Risk budget Turnover
Risk budget	A limit or allocation assigned to a source of portfolio risk, such as an asset, strategy, or factor. $\operatorname{RC}_i=w_i(\Sigma w)_i/\sqrt{w^\mathsf{T}\Sigma w}$	Units and convention Risk contribution has the same volatility units as the portfolio, commonly annualized percentage points; normalized contributions are percentages. Values Normalized contributions commonly sum to 100%; individual contributions can be negative when a position hedges other risk.	Interpretation It attributes marginal portfolio volatility to positions or factors rather than allocating capital alone. Why it matters Equal capital weights need not produce equal risk, particularly when volatilities and correlations differ.	Factor exposure Portfolio optimization Beta neutral
Rolling ICIR	The mean information coefficient divided by its standard deviation over a trailing window, usually annualized. It measures the persistence of ranking skill rather than one period’s IC. $\operatorname{ICIR}_{t,T}=\sqrt{A}\,\overline{\operatorname{IC}}_{t,T}/s(\operatorname{IC}_{t,T})$	Units and convention Dimensionless. A is observations per year, commonly 252 for daily non-overlapping observations. Values Unbounded in principle. Positive is favorable for the stated signal direction; instability increases when the denominator is small.	Interpretation A high value requires positive average rank association that is reasonably consistent through the trailing window. Why it matters It is useful for monitoring signal decay and for distinguishing persistent evidence from a few unusually strong dates.	Information coefficient (IC)Factor timing Expected return
Sharpe ratio	Mean excess return divided by return volatility, expressed on a consistent time scale. $\operatorname{SR}=\sqrt{A}\,\overline{(R_p^{(b)}-R_f^{(b)})}/s(R_p^{(b)}-R_f^{(b)})$	Units and convention Dimensionless. The return frequency, annualization factor A, base currency b, and risk-free convention must be stated. Values Unbounded in principle. Positive means positive average excess return; comparisons require consistent sampling and costs.	Interpretation It measures average excess return per unit of total realized volatility. Why it matters It is a compact risk-adjusted summary, but hides path dependence, tail shape, and estimation uncertainty.	Sortino ratio Maximum drawdown Expected return
Slippage	The signed difference between an intended or reference execution price and the price actually achieved. $s=\operatorname{side}\,(P_{exec}-P_{ref})/P_{ref}$	Units and convention Dimensionless return, usually basis points. Prices and FX conversion must use a consistent quote convention and timestamp. Values Signed and unbounded in theory; positive commonly denotes a cost when side is +1 for buys and −1 for sells.	Interpretation It isolates price deterioration or improvement relative to the selected reference price. Why it matters Small per-trade differences can consume a large share of gross alpha in high-turnover strategies.	Implementation shortfall Turnover Capacity
Sortino ratio	Mean return above a minimum acceptable return divided by downside deviation rather than total volatility. $\operatorname{Sortino}=\sqrt{A}\,\overline{(R_p-R_{MAR})}/\sqrt{\mathbb E[\min(R_p-R_{MAR},0)^2]}$	Units and convention Dimensionless. Returns, minimum acceptable return, time scale, and base currency must be consistent. Values Unbounded in principle and unstable when there are very few downside observations.	Interpretation It penalizes returns below the chosen threshold without treating upside variability as risk. Why it matters It can be more relevant than Sharpe when harmful downside variation is the principal concern.	Sharpe ratio Maximum drawdown Expected return
Tracking error	The standard deviation of active return relative to a benchmark. $\operatorname{TE}=\sqrt{A}\,s(R_p^{(b)}-R_B^{(b)})$	Units and convention Return per year, normally reported in annualized percentage points. Portfolio and benchmark must share base currency b. Values Non-negative. Zero means identical measured returns, not necessarily identical holdings.	Interpretation Higher tracking error means realized performance deviates more widely from the benchmark. Why it matters It connects active portfolio decisions to the variability of benchmark-relative outcomes.	Active share Factor exposure Maximum drawdown
Turnover	The amount of portfolio trading required between two sets of weights, under a stated convention. $\operatorname{TO}_t=\tfrac12\sum_i\|w_{i,t}-w_{i,t^-}\|$	Units and convention Fraction or percentage of NAV/gross notional per rebalance; it may also be annualized. The one-way or two-way convention must be stated. Values Non-negative. It can exceed 100% over a period or at one rebalance for leveraged portfolios.	Interpretation One-way turnover of 0.25 means trading notionals equal to roughly 25% of the chosen capital base. Why it matters Turnover connects weight instability to commissions, spreads, market impact, taxes, and operational load.	Slippage Implementation shortfall Capacity
Universe selection	The point-in-time rules determining which securities are eligible for research or portfolio construction. $U_{i,t}=\mathbf 1\{i\text{ satisfies all eligibility rules at }t\}$	Units and convention Binary indicator for each security and observation date; aggregate universe size is a security count. Values 0 for ineligible and 1 for eligible. Membership must be reconstructed point in time.	Interpretation The universe defines the cross-section against which signals are ranked and portfolios are formed. Why it matters Survivorship, liquidity, listing, country, and data-availability rules can materially change measured factor performance.	Cross-sectional ranking Alpha factor Information coefficient (IC)