Business intelligence
Power BI
KPIs · dashboards · retail
Hello, I’m Jingyi JR Business Analyst — Data, AI & Product Operations.
I help business and technical teams turn complex data into reliable decisions and operational AI products.
Available for permanent roles or work-study opportunities in France French C1 · English C1 · Mandarin
You need reliable decisions, not more data.
I connect business metrics, quality assurance and product delivery so teams can act with confidence.
- ✦Read sales, retail and e-commerce KPIs beyond basic reporting.
- ✦Check data quality before it informs a decision.
- ✦Turn user feedback into tests and product priorities for technical teams.
- ✦Present complex analysis in a clear, useful and actionable format.
Power BIPythonSQLLLM QA
> launching jingyi.exe...
> loading business-analysis modules...
> ready.
[ jingyi ren ]
focus: business analysis · data · AI product operations
experience: Nestlé France · Chanel · Semantikmatch
signals: 50+ dashboards | 10+ KPIs | 200+ incidents
languages: French C1 | English C1 | Mandarin
next objective: contribute to a permanent or work-study role in France
> type “contact” to get in touchMy skills
Analytical, product and business skills that turn data into practical action.
SQL
Query · combine · validate
Panels Python
Pandas · Plotly
AI product quality
LLM QA
Prompts · tests · incidents
API & Salesforce
Systems · flows · operations
Consumer insights
Nielsen Panels · Kantar · category
Tableau
Statistics · data visualisation
Machine Learning
NLP · Deep Learning · XGBoost
My experience
Experience across retail, FMCG and AI product work, connecting data, users and decisions.
August 2025 — January 2026
Semantikmatch
AI Project Assistant
Functional acceptance testing, LLM tests, Sandbox / API / Salesforce integrations and follow-up of more than 200 incidents through to production.
March 2024 — August 2024
Chanel
Business Analyst & Retail Coordination Assistant
Retail and e-commerce KPI tracking for four houses, Power BI, data quality and business / IT coordination.
July 2023 — December 2023
Nestlé France
Assistant Category Manager
Category analysis with Nielsen and Kantar, 50+ dashboards and tracking of sales and consumer KPIs.
My education
2022 — 2025
EDHEC Business School
Master in Management — Data Analysis & AI
Data analysis, applied AI, business intelligence and research focused on business decisions.
Bachelor’s degree
Yanshan University
French Language and Literature
Projects connecting data, business and product
Anonymised case studies focused on method, decisions and outcomes.
Business decisions
Connect indicators to a business question and a concrete action.
Data quality
Validate data and make indicators reliable enough to support decisions.
AI product
Test AI workflows, qualify incidents and make production releases safer.
Customer insights
Turn market data and customer feedback into actionable recommendations.
AI productMaking an AI product more reliable before production
LLM QAAPISalesforceLinear
- Challenge
- Secure AI-product workflows where edge cases, integrations and LLM outputs could degrade the experience before production.
- Approach
- Turn test feedback into actionable tickets and create a common language across product, technical and operations teams.
- Contribution
- I tested workflows in the Sandbox, checked API and Salesforce integrations, evaluated LLM prompts and followed 200+ incidents in Linear through to resolution.
- Outcome
- Continuous visibility on workflow quality and more usable feedback to prioritise fixes before deployments.
!
↗
✦
✓
Key figures
Non-confidential information200+
Incidents tracked
Dev → Prod
Stages
Sandbox & API
Scope
My approach⌄
- Formalised test scenarios covering business workflows and edge cases.
- Checked LLM outputs for consistency and usability.
- Qualified, documented and tracked incidents in Linear.
- Coordinated feedback across Sandbox, API, Salesforce and internal teams.
Customer insightsIdentifying the signals that make a customer review helpful
PythonXGBoostNLPCustomer insights
- Challenge
- Understand which parts of a product review genuinely help other customers make a decision, beyond the star rating alone.
- Approach
- Build a feature set combining transactional information and text characteristics, then compare their predictive contribution.
- Contribution
- For my thesis, I analysed 50,000 Amazon baby-product reviews, created 17 variables and trained an XGBoost model to estimate perceived review helpfulness.
- Outcome
- Verified purchases and images emerged as the strongest signals, followed by review length.
!
↗
✦
✓
Key figures
Non-confidential information50,000
Reviews analysed
17
Variables
XGBoost
Model
My approach⌄
- Prepared and explored a sample of 50,000 product reviews.
- Created variables connected to content, credibility and publication context.
- Trained and interpreted an XGBoost model.
- Translated findings into implications for marketing and e-commerce teams.
Data qualityMaking retail and e-commerce KPIs meaningful
Power BIRetailE-commerceData governance
- Challenge
- Make retail and e-commerce indicators comparable and useful for teams with different operational needs while supporting data quality.
- Approach
- Combine KPI monitoring with close coordination between business and IT stakeholders to clarify definitions, needs and priorities.
- Contribution
- I contributed to tracking indicators for four houses in Power BI, data-governance work and coordination between business and technical teams.
- Outcome
- A more shared view of KPIs and stronger support for retail and e-commerce steering routines.
!
↗
✦
✓
Key figures
Non-confidential information4
Houses
Retail + e-com
Channels
Power BI
BI tool
My approach⌄
- Tracked and consolidated retail and e-commerce indicators in Power BI.
- Contributed to data-governance and data-quality topics.
- Coordinated business needs, reporting and IT teams.
- Adapted analysis to the contexts of four houses.
Business decisionsFrom dashboards to category decisions
Power BINielsenKantarCategory management
- Challenge
- Help a category team distinguish genuinely useful signals across multiple sales and consumer-data sources, including in the analysis of Carrefour’s exit.
- Approach
- Connect market and commercial-performance KPIs to a clear business question, then make the analysis accessible through reusable dashboards.
- Contribution
- I produced more than 50 dashboards for two brands, monitored 10+ sales and consumer KPIs through Nielsen and Kantar, and helped break down the impact of Carrefour’s exit.
- Outcome
- More structured analysis for category discussions and a shared basis for interpreting performance changes.
!
↗
✦
✓
Key figures
Non-confidential information50+
Dashboards
10+
KPIs tracked
2
Brands
My approach⌄
- Built and updated dashboards from sales and consumer indicators.
- Analysed market, category and brand-performance trends.
- Read the impact of a distribution change through a decomposition approach.
- Presented results in a format suited to the needs of a business team.
A few frequently asked questions
Would you like to know more? Contact me directly by email.
- I primarily target Business Analyst, Data & AI Analyst, Product Operations and Marketing / Consumer Insights roles.
- Yes. I am open to permanent and work-study opportunities in France, depending on the team’s needs and the related administrative process.
- I describe the context, my method, tools and non-sensitive outcomes. I do not publish internal data, screenshots or proprietary documents.
- It helps me turn a business need into test scenarios, prioritise quality risks and make communication easier between users, operational teams and technical teams.
Business context
Start with the question behind a KPI: what changed, why it matters and what the team can test next.
Data reliability
Check sources, definitions and breaks in historical data before an insight becomes a decision.
AI product quality
Use representative test scenarios, clear priorities and regression checks before a workflow reaches production.
Cross-functional clarity
Translate complex analysis and feedback into language that business and technical teams can both act on.
Business context
Start with the question behind a KPI: what changed, why it matters and what the team can test next.
Data reliability
Check sources, definitions and breaks in historical data before an insight becomes a decision.
AI product quality
Use representative test scenarios, clear priorities and regression checks before a workflow reaches production.
Cross-functional clarity
Translate complex analysis and feedback into language that business and technical teams can both act on.
Business context
Start with the question behind a KPI: what changed, why it matters and what the team can test next.
Data reliability
Check sources, definitions and breaks in historical data before an insight becomes a decision.
AI product quality
Use representative test scenarios, clear priorities and regression checks before a workflow reaches production.
Cross-functional clarity
Translate complex analysis and feedback into language that business and technical teams can both act on.
Business context
Start with the question behind a KPI: what changed, why it matters and what the team can test next.
Data reliability
Check sources, definitions and breaks in historical data before an insight becomes a decision.
AI product quality
Use representative test scenarios, clear priorities and regression checks before a workflow reaches production.
Cross-functional clarity
Translate complex analysis and feedback into language that business and technical teams can both act on.