10 of 10 Decision Tree Jobs in the South East

of data science & statistical techniques across pricing & underwriting Research and leverage new and existing data sources; capturing and explaining trends with innovative data features Communicate results to key decision makers across the business for action based on the results of pricing analysis Review observed & expected performance of key accounts Collaborate with peers in pricing, underwriting and data science … team members Key Skills and Experience: Previous experience within general insurance pricing Experience with some of the following predictive modelling techniques; Logistic Regression, GBMs, Elastic Net GLMs, GAMs, Decision Trees, Random Forests, Neural Nets and Clustering Experience in statistical and data science programming languages (e.g. R, Python, PySpark, SAS, SQL) A good quantitative degree (Mathematics, Statistics, Engineering, Physics More ❯

of data science & statistical techniques across pricing & underwriting Research and leverage new and existing data sources; capturing and explaining trends with innovative data features Communicate results to key decision makers across the business for action based on the results of pricing analysis Review observed & expected performance of key accounts Collaborate with peers in pricing, underwriting and data science … team members Key Skills and Experience: Previous experience within general insurance pricing Experience with some of the following predictive modelling techniques; Logistic Regression, GBMs, Elastic Net GLMs, GAMs, Decision Trees, Random Forests, Neural Nets and Clustering Experience in statistical and data science programming languages (e.g. R, Python, PySpark, SAS, SQL) A good quantitative degree (Mathematics, Statistics, Engineering, Physics More ❯

SAP/Oracle or similar ERP systems for product, sales and pricing data Proficiency in Python, with some knowledge of querying databases Knowledge of machine learning techniques (clustering, decision trees, neutral networks etc.) and their real-world advantages/drawbacks The make-up of the ideal Data Scientist candidate will include strong problem-solving, confident communication skills and More ❯

Key Skills and Experience: Previous experience within Personal Lines Pricing is advantageous Experience with some of the following predictive modelling techniques; Logistic Regression, GBMs, Elastic Net GLMs, GAMs, Decision Trees, Random Forests, Neural Nets and Clustering Experience in statistical and data science programming languages (e.g. R, Python, PySpark, SAS, SQL) A good quantitative degree (Mathematics, Statistics, Engineering, Physics More ❯

Key Skills and Experience: Previous experience within Personal Lines Pricing is advantageous Experience with some of the following predictive modelling techniques; Logistic Regression, GBMs, Elastic Net GLMs, GAMs, Decision Trees, Random Forests, Neural Nets and Clustering Experience in statistical and data science programming languages (e.g. R, Python, PySpark, SAS, SQL) A good quantitative degree (Mathematics, Statistics, Engineering, Physics More ❯

Key Skills and Experience: Previous experience within Personal Lines Pricing is advantageous Experience with some of the following predictive modelling techniques; Logistic Regression, GBMs, Elastic Net GLMs, GAMs, Decision Trees, Random Forests, Neural Nets and Clustering Experience in statistical and data science programming languages (e.g. R, Python, PySpark, SAS, SQL) A good quantitative degree (Mathematics, Statistics, Engineering, Physics More ❯

NumPy, scikit-learn, PyTorch, and Hugging Face Transformers. Ability to write clean, modular, and testable code. Traditional Machine Learning Models: Experience with regression (linear, ridge), classification (logistic regression, decision trees, random forests), clustering (k-means, DBSCAN), and time-series forecasting (ARIMA, Prophet). Model evaluation, tuning, and deployment. Business Requirement Translation: Ability to convert business problems into data More ❯

like pandas, NumPy, scikit-learn, PyTorch, and Hugging Face Transformers. Writing clean, modular, and testable code. Traditional Machine Learning Models: Experience with regression (linear, ridge), classification (logistic regression, decision trees, random forests), clustering (k-means, DBSCAN), and time-series forecasting (ARIMA, Prophet). Model evaluation, tuning, and deployment. Business Requirement Translation: Ability to convert business problems into data More ❯

like pandas, NumPy, scikit-learn, PyTorch, and Hugging Face Transformers. Writing clean, modular, and testable code. Traditional Machine Learning Models: Experience with regression (linear, ridge), classification (logistic regression, decision trees, random forests), clustering (k-means, DBSCAN), and time-series forecasting (ARIMA, Prophet). Model evaluation, tuning, and deployment. Business Requirement Translation: Ability to convert business problems into data More ❯

like pandas, NumPy, scikit-learn, PyTorch, and Hugging Face Transformers. Writing clean, modular, and testable code. Traditional Machine Learning Models: Experience with regression (linear, ridge), classification (logistic regression, decision trees, random forests), clustering (k-means, DBSCAN), and time-series forecasting (ARIMA, Prophet). Model evaluation, tuning, and deployment. Business Requirement Translation: Ability to convert business problems into data More ❯