Data Scientist

About Wego We’re on a mission to help people discover the real value of travel — to inspire, to give more reasons, to make it easy — for you to travel. Our company was founded back in 2005, and since then, we’ve imagined and created some of the most well-loved products for travellers all around the world. Today, Wego is the number 1 travel metasearch engine in the Middle East. There are millions of users on Wego every month — people who travel for adventure, for work, for family and for many other reasons. That’s why we work tirelessly to make your experience of planning & booking flights, hotels and trips as seamless as possible. About the Role The Data Team supports Wego in a multitude of analytical projects and initiatives, with core functions ranging from data analytics, data engineering and data science. We also support all of our internal stakeholders, from product, marketing, finance, sales and operations, to help them uncover important business insights to make well-considered data-driven decisions. This role is specifically working with the Lead of Data Science and Innovation residing within the core Data Team, which we’re expanding out to help support the development of new data science and analytical initiatives. These initiatives help our company better analyze and understand the customer user journey and their travel intentions, to better curate better optimisations and user experience on our travel platform. Location This position is available in both remote and in-office arrangements in our office in Kuala Lumpur. For remote arrangements, we strongly prefer that you are located somewhere within the GMT+7 to GMT+9 time zones so that there is a decent overlap in working hours with the rest of the team. Responsibilities

• Support the development and maintenance of advanced analytics and new data science initiatives, like personalisation, predictive customer lifetime value, travel persona segmentation, recommended sort order, rate cache optimisation, experimentation with A/B testing and propensity models.
• Analyze our datasets to uncover key insights and recommendations through the use of effective data analysis and visualizations.
• Assist in building out new analytical tables and develop ETL/ELT pipelines. Investigate potential data issues and perform exploratory data analysis in verifying certain hypotheses.
• Understand business/technical use cases of internal stakeholders, to be able to contextually curate data science solutions/statistical approaches. 
• Writing out and documenting our approaches, to support the communication and presentation of data science solutions of our use cases to stakeholders. 
• Review data science research and industry white papers to consolidate and identify best practices/approaches that we can practically apply in certain areas.
• Help support and monitor our existing and new statistical/ML solutions, in its productionisation (MLOps), assessing for model drift and evaluating KPIs/success metrics.

• Aptitude or inclination towards mathematics/statistics, with an adaptable coding ability (i.e. Python).
• Good ability in using more complex SQL functions (i.e. windowing, DDL, DML syntax). Be able to understand lengthier, nested queries and visualize what each section is specifically doing to deliver the precise calculation that you want.
• Able to comfortably and intuitively work with disparate kinds of datasets, to independently figure out how best to manipulate them to arrive at insights.
• Know how to generally develop dashboards (i.e. Looker, PowerBI, Tableau) to showcase pertinent insights. Not necessary for specific visualization tool knowledge.
• Able to communicate effectively, on systematically breaking down a problem, articulating/distilling key issues and brainstorming solutions, especially as we deal with more complex data science problems and considerations.
• Keen on supporting the development of new areas of analyses (i.e. customer-centric RFM, cross-sell propensity), as at times, we are trying to introduce and convince internal stakeholders of new analytical approaches/KPIs.
• Proactive and adaptable in the face of unknowns. Good troubleshooting ability in dealing with problems.
• Have a general understanding/inclination of how data science models/statistical approaches work (i.e. Neural Networks, Random Forests, Linear Regression, Principal Component Analysis, K Means), hyperparameter tuning and model evaluation metrics (i.e. Accuracy, Confusion Matrix). 

• Google BigQuery
• Looker
• Tableau
• Python
• Github
• Airflow