Machine Learning Lead

Company introduction Our mission at Umba is to use machine learning to allow us to create intelligent, affordable financial products for emerging markets. Umba launched into the Kenyan market in November 2018, and offers a number of digital banking products to its users through an Android App. This platform uses machine learning and big data to build credit scores to optimize risk exposures and allows users to apply, receive and repay microloans and through their smartphone. Once a user creates an account we validate their information and make lending decisions based on the information they give us and hundreds of data points we take from their smartphone with their permission. Our machine learning models are in a state of constant improvement and we use AI and automation to deliver the lowest cost banking solutions for our growing customer base. We have built out a large data collection platform, with our data warehouse storing over 100m rows of data for accurate credit scoring. Job Description We are looking for a Data Scientist that will help us discover the information hidden in vast amounts of data, and help us make smarter decisions to deliver even better products. Your primary focus will be in applying data mining techniques, doing statistical analysis, and building high quality prediction systems integrated with our products. Our most complex system is our risk model, your day to day will include feature generation and model training using machine learning techniques, developing A/B testing procedures, implementing automated model retraining and creating new projects based on your findings. You will be working with a small, but highly technical team. We have 170,000 users and work to ensure continuous uptime, and constant improvement. We train and deploy new machine learning models regularly and subscribe to data driven decision making, you will not be just an implementer, but a valued opinion at the table. Responsibilities Selecting features, building and optimizing classifiers using machine learning techniques Data mining using state-of-the-art methods Extending company's data with third party sources of information when needed Enhancing data collection procedures to include information that is relevant for building analytic systems Processing, cleansing, and verifying the integrity of data used for analysis Doing ad-hoc analysis and presenting results in a clear manner Creating automated anomaly detection systems and constant tracking of its performance Skills and Qualifications At least 2 years of recent hands-on coding and software design A track record of projects completed on time - you are a flawless executor, not a procrastinator You find satisfaction in a job well done and want to solve head-scratching challenges Excellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Decision Forests, etc. Experience with common data science toolkits, such as R, Weka, NumPy, MatLab, etc. Excellence in at least one of these is highly desirable Experience with machine learning frameworks such as Scikit-Learn and Tensorflow Experience with data visualisation tools, such as D3.js, GGplot, Matplotlib etc. Experience with relational databases such as Postgres, MySQL etc. Proficiency in using query languages such as SQL Good applied statistics skills, such as distributions, statistical testing, regression, etc. Good scripting and programming skills are a bonus Data-oriented personality Great communication skills You're so much fun to work with, that if you were working on the weekend, we'd want to join you.