DE&A - AIML - Data Science - Machine Learning
Summary
Build and validate ML models (XGBoost, Prophet, survival analysis) to forecast demand, inventory, and time-to-event outcomes, then explain results to business stakeholders using SHAP and causal analysis.
Data Scientist
Role Overview Responsible for designing, building, and validating predictive and explanatory models that generate actionable business insights. Works closely with business stakeholders to ensure model outputs are accurate, interpretable, and aligned to real-world decision-making.
Experience Required: 3–5 years
Key Responsibilities
Perform exploratory data analysis and feature engineering across multiple data sources
Design, train, validate, and backtest supervised ML models for classification and regression tasks
Build time-series and probabilistic forecasting models for demand and inventory signals
Develop survival analysis models to predict time-to-event outcomes
Build explainability pipelines (SHAP) to translate model outputs into business-readable root cause attribution
Conduct causal analysis and process mining to identify workflow patterns driving business outcomes
Validate model outputs with business SMEs and refine based on feedback
Define and agree model performance thresholds, feature importance priorities, and acceptance criteria with client stakeholders
Required Skills
3–5 years of experience in data science, machine learning, or advanced analytics
Strong experience in supervised ML (XGBoost, LightGBM, Random Forest, scikit-learn)
Experience with time-series forecasting (Prophet, ARIMA) and survival analysis
Proficiency in SHAP and other model explainability frameworks
Strong Python skills (pandas, numpy, scikit-learn)
Ability to communicate complex model outputs clearly to non-technical business stakeholders
Experience in supply chain, retail, or inventory analytics preferred
Data Scientist
Role Overview Responsible for designing, building, and validating predictive and explanatory models that generate actionable business insights. Works closely with business stakeholders to ensure model outputs are accurate, interpretable, and aligned to real-world decision-making.
Experience Required: 3–5 years
Key Responsibilities
Perform exploratory data analysis and feature engineering across multiple data sources
Design, train, validate, and backtest supervised ML models for classification and regression tasks
Build time-series and probabilistic forecasting models for demand and inventory signals
Develop survival analysis models to predict time-to-event outcomes
Build explainability pipelines (SHAP) to translate model outputs into business-readable root cause attribution
Conduct causal analysis and process mining to identify workflow patterns driving business outcomes
Validate model outputs with business SMEs and refine based on feedback
Define and agree model performance thresholds, feature importance priorities, and acceptance criteria with client stakeholders
Required Skills
3–5 years of experience in data science, machine learning, or advanced analytics
Strong experience in supervised ML (XGBoost, LightGBM, Random Forest, scikit-learn)
Experience with time-series forecasting (Prophet, ARIMA) and survival analysis
Proficiency in SHAP and other model explainability frameworks
Strong Python skills (pandas, numpy, scikit-learn)
Ability to communicate complex model outputs clearly to non-technical business stakeholders
Experience in supply chain, retail, or inventory analytics preferred
Data Scientist
Role Overview Responsible for designing, building, and validating predictive and explanatory models that generate actionable business insights. Works closely with business stakeholders to ensure model outputs are accurate, interpretable, and aligned to real-world decision-making.
Experience Required: 3–5 years
Key Responsibilities
Perform exploratory data analysis and feature engineering across multiple data sources
Design, train, validate, and backtest supervised ML models for classification and regression tasks
Build time-series and probabilistic forecasting models for demand and inventory signals
Develop survival analysis models to predict time-to-event outcomes
Build explainability pipelines (SHAP) to translate model outputs into business-readable root cause attribution
Conduct causal analysis and process mining to identify workflow patterns driving business outcomes
Validate model outputs with business SMEs and refine based on feedback
Define and agree model performance thresholds, feature importance priorities, and acceptance criteria with client stakeholders
Required Skills
3–5 years of experience in data science, machine learning, or advanced analytics
Strong experience in supervised ML (XGBoost, LightGBM, Random Forest, scikit-learn)
Experience with time-series forecasting (Prophet, ARIMA) and survival analysis
Proficiency in SHAP and other model explainability frameworks
Strong Python skills (pandas, numpy, scikit-learn)
Ability to communicate complex model outputs clearly to non-technical business stakeholders
Experience in supply chain, retail, or inventory analytics preferred