About the Role:
As a Data Scientist you will help Snapp discovering hidden patterns in vast amounts of data generated by both costumers and drivers. This will help Snapp to make right decisions in delivering quality products and services to its stakeholders. In the role, you will mine various types of data, from structured to unstructured using data mining techniques, doing statistical analysis and building high quality prediction models to support initiatives that add business value and drive bottom-line growth.
• Work with stakeholders throughout the organization to identify opportunities for leveraging company data to drive business solutions.
• Identify major data sources at Snapp, and then, know, collect, cleanse and aggregate all types of data needed for analysis and mining
• Mine and analyze data using state-of-the-art algorithms on large datasets to extract trends and discovering patterns improving our product and services performance.
• Assess the effectiveness and accuracy of data sources and data gathering techniques.
• Design and develop predictive models using machine learning algorithms to increase and optimize customer experiences and other business outcomes..
• Develop processes and tools to monitor and analyze model performance and data accuracy.
• Design of rigorous experiments and interpret the results to draw detailed and actionable conclusions
• Promote continuous improvement through data mining and analytic Present findings in a clear and concise manner to senior management to influence and strengthen business decisions
• BS or MS in Computer Science/Engineering or equivalent relevant experience
• 4 years of experience on collecting, developing, analyzing, manipulating, and drawing insights from data. Also, demonstrated achievements in the fields of data science
• Experience with applied statistics skills, such as distributions, statistical testing, hypotheses validation, regression, etc.
• Experience with a broad range of modeling techniques both supervised (knn, svm, trees and ensemble methods, deep learning, etc) and unsupervised methods ( kmeans, hierarchical clustering, dbscan, etc)
• Having experience in developing effective models in applications such as fraud detection and anomaly detection
• Experience with feature selection and reduction algorithms
• Practical knowledge and experience of Python, specifically data science packages such as numpy, pandas, scipy, scikit-learn, NLTK, tensorflow, etc.
• Demonstrated experience working with large, complex datasets using scalable tools related to machine learning and big data
• Strong ability to write complex, efficient, and eloquent SQL queries to extract data
• Experience with Hadoop platform
• Experience with Hive, Kafka and Spark tools Eagerness to learn and exploration