Data Envelopment Analysis (DEA): Efficiency with Python

[jitexsubtra]

Data Envelopment Analysis (DEA): Efficiency with Python
Published 10/2026
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch
Language: English | Duration: 1h 33m | Size: 659.67 MB

Benchmark stores, bank branches and hospitals with exact linear programming: CCR, BCC, super-efficiency and Python code

What you'll learn
Formulate and solve linear programs in Python with SciPy, and read shadow prices to see which constraint is worth relaxing
Measure the relative efficiency of stores, bank branches or any comparable units with DEA, and identify the peers each one should learn from
Turn the DEA efficiency ratio into a linear program step by step, and see why the weights and envelopment forms give the same score
ell a management problem from a scale problem by comparing the CCR and BCC models, so you never blame a manager for the size of a unit
Rank units tied at 100% with super-efficiency, and add management judgment to the model with assurance regions
Know where AI helps in an efficiency study and where it doesn't, and validate DEA results with a Monte Carlo simulation

Requirements
Basic high school math: fractions, percentages and reading a simple chart. Every concept is built from zero, including linear programming.
No prior Python experience needed to follow the course. To run the code yourself, a free Python installation or Google Colab is enough.

Description

Is this unit underperforming because of bad management, or because of something it never controlled?
Every network of comparable units faces this question: retail chains, franchises, bank branches, hospitals, schools. Get the answer wrong, and you either let a badly run unit off the hook, or you blame a manager for a problem that was never theirs to fix.

Simple ratios like sales per square meter or revenue per employee can't answer it. They collapse several inputs into one number and hide what is really driving performance.Data Envelopment Analysis (DEA) can. It compares each unit with its real peers, using every input and every output at once, and tells you not only how efficient a unit is, but which units it should learn from.

This course builds DEA from zero. It doesn't assume any background in optimization: we start withlinear programming, using a simple furniture factory, and solve it inPython with SciPy. Then we build DEA step by step

-Cosmetics Chain Example: why single ratios mislead, and what an efficient frontier is

-Bank Branches Example: drawing the frontier by hand and measuring efficiency as a distance

-Mathematical Resolution: turning the efficiency ratio into a linear program a computer solves exactly

-Analysis of a Bank Branch: the full model in code, and how a business rule changes the results

-Returns to Scale: separating a management problem from a size effect with the CCR and BCC models

-Super-Efficiency: ranking the units that tie at 100%

-Assurance Regions: adding real business judgment to the weights, and reading a full diagnosis of one store

-DEA Applications: retail, banking, healthcare, education, real estate and public services

-DEA and AI: where artificial intelligence helps, where it doesn't, and how to validate DEA with a Monte Carlo simulation

-Espelho Demo: a complete efficiency diagnosis running in a real browser application

Every concept is explained with worked examples and real numbers, and every calculation is exact and reproducible: the same answer, every time, for the same data.

About the instructor
Michel Janos is an engineer, consultant and former corporate executive, and the author of the book seriesMathematics for the 21st Century , a finalist for the Jabuti Prize, Brazil's most important literary award. He applies DEA to real retail networks through his efficiency diagnostic tool, Espelho.

Who this course is for
Managers and owners of retail chains, franchises, bank branches, clinics or schools who want to know which units are truly underperforming, and why
Consultants and business analysts who need a rigorous, explainable method to benchmark units and support their recommendations with numbers
Students of engineering, economics, business or operations research who want to learn DEA and linear programming through real, worked examples
Data scientists looking for an exact optimization method for efficiency analysis, and a clear view of where machine learning fits and where it doesn't

Homepage

Code:

https://www.udemy.com/course/data-envelopment-analysis-dea-efficiency-with-python/

Code:

https://rapidgator.net/file/ec8a20a81231f37c005834b9a9641ef2/Data_Envelopment_Analysis_(DEA)_Efficiency_with_Python.rar.html

https://nitroflare.com/view/E8AEBCCAEEE8A77/Data_Envelopment_Analysis_%28DEA%29_Efficiency_with_Python.rar