Kr Beneish

B+ 90 completed
Data Tool
mobile_app / python · tiny
30
Files
2,360
LOC
2
Frameworks
5
Languages

Pipeline State

completed
Run ID
#370986
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
60.67
Framework unique
Isolation
Last stage change
2026-05-10 03:35:17
Deduplication group #59364
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionMobile App
Powered by Repobility — scan your code at https://repobility.com

AI Prompt

Create a Python script that calculates the Beneish M-Score for Korean IFRS companies. I need a function that takes a pandas DataFrame as input, which must contain 14 specific columns like `corp_code`, `year`, `receivables`, and `net_income`. The function should compute the 8 components, the composite M-Score, and a binary flag. Please ensure the output DataFrame includes columns for `dsri`, `gmi`, `aqi`, `sgi`, `depi`, `sgai`, `lvgi`, `tata`, `m_score`, and `flag`. I should be able to optionally pass a specific threshold, like -2.45 for KOSDAQ data.
python pandas finance scoring machine-learning financial-analysis m-score korean-ifrs
Generated by gemma4:latest

Catalog Information

Calculate the Beneish M‑Score for Korean IFRS companies to assess potential earnings manipulation.

Description

This tool computes the Beneish M‑Score, a statistical indicator used to detect earnings manipulation, specifically for companies listed on the Korean KOSPI and KOSDAQ exchanges that report under IFRS. It ingests financial statement data, applies the standard Beneish formula, and outputs a score along with diagnostic ratios. The score helps analysts flag firms that may be engaging in aggressive accounting practices. It is designed for investors, risk managers, and financial researchers who need a quick, automated assessment of Korean corporate financial health. The implementation relies on Python’s data‑science libraries for robust calculations and easy integration into existing workflows.

الوصف

يُعدّ هذا الأداة حلاً لحساب درجة بينيش، وهو مؤشر إحصائي يُستخدم لاكتشاف التلاعب بالأرباح، مع تركيز خاص على الشركات المدرجة في بورصتي كوسبي وكوسداك الكورية التي تتبع المعايير الدولية للتقارير المالية. يستورد الأداة بيانات القوائم المالية، ويطبق صيغة بينيش القياسية، ثم يُخرج نتيجة الدرجة مع نسب تشخيصية توضح نقاط الضعف المحتملة. يتيح هذا التقييم للخبراء الماليين تحديد الشركات التي قد تتبع ممارسات محاسبية متشددة. يُصمم الأداة لتلبية احتياجات المستثمرين ومديري المخاطر والباحثين في مجال المالية الذين يحتاجون إلى تحليل سريع وموثوق للبيانات المالية الكورية. يعتمد التنفيذ على مكتبات علم البيانات في لغة بايثون لضمان دقة الحسابات وسهولة دمجها في سير العمل الحالي.

Novelty

6/10

Tags

financial-analysis earnings-manipulation-detection korean-market ifrs-compliance risk-assessment corporate-finance accounting-ratios investment-screening

Technologies

numpy pandas

Claude Models

claude-opus-4.6 claude-sonnet-4.6

Quality Score

B+
89.9/100
Structure
92
Code Quality
100
Documentation
80
Testing
85
Practices
78
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (117% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Low average code complexity \u2014 well-structured code
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Security & Health

4.6h
Tech Debt (D)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (5)
Want fix-PRs on findings? Install Repobility's GitHub App · github.com/apps/repobility-bot
MIT
License
7.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
58.7%
markdown
35.5%
yaml
3.1%
toml
2.6%
json
0.2%

Frameworks

Expo pytest

Concepts (2)

Scored by Repobility's multi-pass pipeline · https://repobility.com
CategoryNameDescriptionConfidence
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
auto_descriptionProject DescriptionBeneish M-Score for Korean IFRS (KOSPI/KOSDAQ) companies.80%
auto_categoryMobile Appmobile70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/95194.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV