We are looking for a Stockholm-based Master’s student in Data Science, Mathematics, Finance, or a related field to undertake a degree project focused on improving our rent prediction algorithm. The goal is to enhance the accuracy of rent estimates by developing models that take into account multiple variables such as property features, location, market trends, and tenant demand. The successful candidate will work at our office during the Spring semester, collaborating closely with our data science and product teams to push the boundaries of our current predictive models.

What You’ll Work On

• Research, design, and prototype advanced machine learning models to improve the accuracy of rent predictions.
• Experiment with different techniques, such as regression models, time-series forecasting, and neural networks, to handle complex and dynamic pricing patterns.
• Leverage external data sources like real estate trends, economic indicators, and competitor pricing to enhance the prediction model.
• Develop methods for incorporating geographical features (e.g., proximity to schools, parks, public transportation) into the predictive model.
• Test and validate models using historical data and back-testing to ensure robustness in real-world applications.
• Work closely with the product and development teams to integrate the improved rent prediction algorithm into Qasa’s platform.
• Continuously analyze and refine the model’s performance by monitoring real-time data and user feedback.

You’ll Be a Great Fit If You

• Have experience with machine learning libraries (e.g., scikit-learn, TensorFlow, PyTorch) and statistical modeling techniques.
• Enjoy working with Python, Ruby on Rails, PostgreSQL, or similar tools and databases.
• Are familiar with time-series analysis, regression models, and forecasting techniques.
• Have an interest in real estate markets, pricing strategies, and data-driven decision-making.
• Can communicate complex findings clearly to technical and non-technical stakeholders.
• Enjoy solving practical, real-world problems using a mix of theoretical and empirical approaches.

What We Offer

• A chance to work on a high-impact project that shapes the future of rental pricing in the long-term rental market.
• Mentorship from experienced data scientists and access to cutting-edge technologies.
• A collaborative and innovative work environment that encourages creativity.
• Potential for future employment opportunities at Qasa.

🎓Previous Master’s Theses

At Qasa, we’ve had a strong history of collaborating with Master’s students on impactful projects. Here are some of the recent theses completed at Qasa:

• Automated Home Review: Eric Dahlgren developed a system to review home ads before they are published. Using XGBoost and SHAP, an interpretable anomaly detection model was built to automate ad reviews. The model not only scores ads but also provides human-readable explanations to assist decision-making. You can read the thesis here: Enhancement of an Ad Reviewal Process through Interpretable Anomaly Detecting Machine Learning Models
• Rent Prediction: Vasigaran Senthilkumar focused on improving house rental price predictions by incorporating external features such as walk scores and interest rates. The work also introduced methods for handling uncertainty in predictions, including generating prediction intervals and managing uncertain rent data to enhance model adaptability and generalization. You can read the thesis here: Enhancing House Rental Price Prediction Models for the Swedish Market
• Recommendation Systems: Julia Byström created and A/B tested (in production!) two new algorithms to improve tenant rankings for landlords in our “Find tenant” feature. The algorithms were rigorously tested and deployed in production, contributing significantly to our recommendation systems. You can read the thesis here: Probabilistic Weighting and Deferred Acceptance in Reciprocal Recommendations