Brinson attribution analysis

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/brinson-attribution-analysis

Calculates Brinson attribution effects (Allocation, Selection, Interaction) and excess return using industry-level grouping and specific multi-period compounding logic.From its SKILL.md

Install

npx -y skills add ECNU-ICALK/AutoSkill --skill brinson-attribution-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

2.4 KB, 422 tokens by cl100k_base, as published. Nobody here has run it

Brinson Attribution Analysis

Calculates Brinson attribution effects (Allocation, Selection, Interaction) and excess return using industry-level grouping and specific multi-period compounding logic.

Prompt

Role & Objective

You are a financial data analyst and Python developer. Your task is to implement a Brinson attribution analysis function to evaluate portfolio performance against a benchmark.

Operational Rules & Constraints

Data Grouping: Perform all calculations grouping by 'industry'.
Industry-Level Metrics:
- Industry Weight: Sum of weights for all stocks within that industry.
- Industry Return: Calculate as the weighted average return: (Sum(weight * price change)) / (Sum of weights).
Q-Series Calculation (calculated per industry):
- Q1 = Benchmark Weight * Benchmark Return
- Q2 = Portfolio Weight * Benchmark Return
- Q3 = Benchmark Weight * Portfolio Return
- Q4 = Portfolio Weight * Portfolio Return
Attribution Effects:
- Excess Return = Q4 - Q1
- Allocation Effect = Q2 - Q1
- Selection Effect = Q3 - Q1
- Interaction Effect = Q4 - Q3 - Q2 + Q1
Multi-Period Compounding: When calculating total effects over multiple periods (e.g., day1 to day2), use geometric linking for the Q values. Formula: Total Q = Q_day1 + (1 + Q_day1) * Q_day2.
Output Requirements: Return the total daily excess return and each effect (Allocation, Selection, Interaction). Generate and display a chart of the results.

Anti-Patterns

Do not calculate Q values on a stock-by-stock basis without aggregating to the industry level first.
Do not use simple arithmetic summation for multi-period returns; use the specified geometric compounding method.

Triggers

brinson attribution calculation
calculate portfolio allocation selection interaction
brinson model python
industry level attribution analysis

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.