Senior Data Scientist

Data science is at the heart of decision making in Sky and drives many decisions across marketing, customer interactions and customer services at Sky. We are scaling up our data science practice to transform how we manage customers across all life cycles for both experience profitability. We have built and successfully deployed intelligence into Sky and are already delivering realisable value into the business. We gather a very large amount of data on customer behaviours and interactions and are looking for data scientists to extract value from our data assets and maximise customer value.

Job Description

• Responsible for developing and driving actionable customer intelligence from our core data assets using advanced analytics

• Develop advanced analytics algorithms exploiting our rich data assets including product holding, demographics, product usage, customer service interactions and customer metrics

• Develop predictive models for churn prediction, lifetime value estimation, customer segmentation and other consumer-focused use cases

• Collaborate with stakeholders to define project objectives, develop analytical frameworks, and translate business requirements into analytical solutions

• Engage with our technology teams and data engineers to build compliant, efficient and scalable solutions for managing customer treatments at Sky

• Strengthen our internal data science capabilities by continuously innovating and driving new ideas, engaging in training and development of our people

• Leading projects with 1-2 team members, planning tasks and delegating appropriately

Requirements

• Expertise in at least two advanced analytical areas including, but not limited to Predictive Modelling, Optimisation, AI and Graph Analysis

• Experience building and deploying advanced analytics solutions at a large scale (preferably B2C) cloud environment

• Ability to quickly understand a business objective, problem solving to create an analytical solution and stakeholder communication are essential

• Commercial knowledge and applications of data science to drive commercial value is a must – everything we do drives value into the business

• Experience in deploying commercially viable applications using deep learning techniques combining structured and unstructured data is desirable

• Experience in data engineering, data modelling for advanced analytics, data processing on cloud, model management and app deployment on cloud is desirable

Skills

• Programming for modelling and/or data analysis, ideally Python (essential)

• Experience with Machine Learning libraries such as scikit-learn, XGBoost, Keras, Tensorflow etc. (essential)

• Experience using SQL for data extraction, feature development etc. (essential)

• Experience creating machine learning pipelines including raw data, features, model building and testing (essential)

• Experience on Google Cloud Platform e.g. BigQuery, GCS, Datalab, Dataproc, Cloud ML (desirable)

• Experience deploying machine learning pipelines for real-world applications (useful)

• Experience with big data solutions e.g. Spark, Hadoop, MapReduce (useful)

• Other programming experience e.g. SAS, C++, JavaScript (useful)

Analysis:

• Machine learning - Supervised/unsupervised learning, regression, neural networks, decision trees, random forests, boosting, SVM, clustering (essential)

• Deep learning – CNN, RCNN, LSTM, Autoencoder (desirable)

• NLP/Text mining – Bag of Words, text embedding, sentiment analysis (desirable)

• Statistical modelling– GLM, Bayesian hierarchical models (useful)

Soft skills

• Excellent communication with both technical team members and non-technical stakeholders

• Ability to break down complex problems into manageable tasks