Paper: arXiv 2307.01719
Authors: Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu, David, Wang, Michael O’Leary
Abstract
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments. This document provides a user guide for MOPO-LSI version 1.0, including problem setup, workflow and the hyper-parameters in configurations.
Complexity vs Empirical Score
- Math Complexity: 6.5/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper introduces substantial mathematical formulation for multi-objective optimization (weighted sums, convex optimization, MOEA algorithms) but provides only a user guide and workflow description, lacking backtesting results, performance metrics, or implementation-heavy data processing details.
Research Flowchart
flowchart TD A["Research Goal<br>Optimize Sustainable Investment<br>Portfolios"] --> B["Inputs: ESG Scores &<br>Financial Data"] B --> C["Methodology: Multi-Objective<br>Optimization Setup"] C --> D["Computation:<br>MOPO-LSI Engine"] D --> E["Outputs: Pareto-optimal<br>Portfolios"] E --> F["Outcomes: Trade-off Analysis<br>between Return & Sustainability"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes MOPO-LSI, an open‑source multi‑objective portfolio optimization library for sustainable investments.
Source sentence
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments.
Assumes 1
- The library assumes that ESG scores for each mutual fund are available and can be categorized as positive or negative factors. data
Source sentence
This document provides a user guide for MOPO-LSI version 1.0, including problem setup, hyper-parameters and example of the outputs. arXiv:2307.01719v2 [q-fin.PM] 12 Jul 2023 2 Authors Suppressed Due to Excessive Length 2 MOPO-LSI: Problem Setup The MOPO-LSI library facilitates asset allocations for a collection of mutual funds, where the dataset provides ESG scores for each mutual fund. These ESG scores are
Data
- SampleData folder alternative public
Source sentence
4.1 Data Format A sample data set was provided in the ”data/SampleData” folder.
- funds.csv fundamentals public
Source sentence
Any other practice should follow the format of the following three data files: – funds.csv refers to a list of mutual funds as candidates in portfolio optimization. The system runs significantly slowly if it is turned on. yaml/System.yaml Inputs and Outputs: – seed: seed to be used in random process – model: an algorithm or solution to run, options: WeightedSum, NSGA2, SMSE-MOA, AGEMOEA2 – dataset: assign the data
- cov matrix.csv fundamentals public
Source sentence
The system runs significantly slowly if it is turned on. yaml/System.yaml Inputs and Outputs: – seed: seed to be used in random process – model: an algorithm or solution to run, options: WeightedSum, NSGA2, SMSE-MOA, AGEMOEA2 – dataset: assign the data set name which also refers to the subfolder name in folder ”data” – data funds: funds.csv, the list of funds and ESG scores – data cov matrix: cov matrix.csv,
- asset allocation.csv benchmark public
Source sentence
The system runs significantly slowly if it is turned on. yaml/System.yaml Inputs and Outputs: – seed: seed to be used in random process – model: an algorithm or solution to run, options: WeightedSum, NSGA2, SMSE-MOA, AGEMOEA2 – dataset: assign the data set name which also refers to the subfolder name in folder ”data” – data funds: funds.csv, the list of funds and ESG scores – data cov matrix: cov matrix.csv,
Costs
Not applicable
Finds 3
- The library can compute a single optimal solution using a conic solver for the quadratic convex optimization problem. theoretical
Source sentence
The output in this scenario will be a single optimal solution.
- Given a single optimal solution, the library can compare it with a standard non‑ESG benchmark, output evaluation metrics such as tracking error and improvement ratios, and return the top‑N mutual funds for investment. performance
Source sentence
By given a single optimal solution, the library can com-pare it with the standard benchmark (i.e., a non-ESG optimized solution associated with a specific risk level), output evaluation metrics (i.e., tracking error, improve-ment ratio on each ESG factor), and finally return the top-N mutual funds for in-vestments.
- Using the weighted‑sum method on sample data, the library reports gain values defined as the weighted average of improvement ratios over positive and negative ESG groups. performance
Source sentence
An example of the outputs by using the sample data and the weighted sum method in MOPO-LSI can be observed from Figure 2, where the gain values MOPO-LSI: A User Guide 5 refer to the weighted average of the improvement ratios over each ESG groups (i.e., positive and negative ESGs).
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 10 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.