Lab · Module 06 of 06

Attribution Analysis.

Decompose. Explain. Improve. Know what worked, and why.

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

What it is

A portfolio performance attribution framework that explains where your returns came from: it decomposes a portfolio's active return against a benchmark with Brinson-Fachler and a factor model, together or on their own.

How you run it

Entirely from an Excel workbook with no code required, or programmatically in Python.

It prevents

Selling factor beta as if it were alpha.

Two methods.

Two complementary methodologies, run together or independently. Every input is aligned to a common date range before anything is computed.

Brinson-Fachler.

Allocation, selection and interaction effects, per asset and per date. The effects add up exactly to portfolio return minus benchmark return.

Factor model.

The contribution of each style and industry factor, and the stock-specific residual that is left.

Features.

  1. Configurable from an Excel parameters workbook, with no code required to run an analysis, or directly from a Python script. A command line initializes projects (init excel) and updates templates.

  2. Brinson-Fachler attribution: breaks active return into allocation, selection and interaction effects, computed per asset and per date and aggregated over time. The effects add up exactly to portfolio return minus benchmark return.

  3. Factor model attribution: decomposes portfolio return into per-factor contributions plus an idiosyncratic residual, using your own factor return series (style factors such as size, momentum, beta, residual volatility and value, plus industry factors).

  4. Cumulative and percentage views: factor contributions are accumulated over time and expressed as a share of total return, so you can see how much of performance each factor explains and how much is stock-specific.

  5. Independent methodology switches: turn Brinson-Fachler and the factor model on or off from the workbook, to run either analysis alone or both side by side.

  6. Interactive dashboards for exploring factor model results, served locally on a configurable port. Static plots are produced for Brinson-Fachler-only runs.

  7. A PyArrow-based engine with pandas reference implementations, behind clean interfaces that make each methodology easy to extend.

  8. Robust data handling: horizontal or vertical weight files detected automatically, configurable date and price columns, every input aligned to a common date range, and start and end dates set by hand or derived from the data.

What it reads.

Market data

CSV or Parquet, one file per ticker with date and price. Returns are computed internally.

Portfolio and benchmark weights

CSV or Excel: weights by rebalancing date.

Benchmark returns

CSV, daily.

Factor returns

CSV, one file per factor, with per-asset returns.

Configuration

An Excel workbook, or configuration in Python.

Everything you need to get started.

Attribution Analysis comes with the Investment Lab licence.