We are seeking a highly skilled and experienced Machine Learning Engineer and/or Data Analyst to develop a sophisticated similarity scoring algorithm for residential real estate in the USA. This algorithm will be the backbone of a ranking system designed to compare properties based on a range of features, including both numerical and categorical data. The ideal candidate will have a strong background in boosted tree algorithms and a proven track record of working with large data sets for machine learning purposes.
Key Responsibilities:
Algorithm Development:
-Design and implement a similarity scoring algorithm using boosted tree methodologies.
-Ensure the algorithm effectively handles both numerical and categorical data, including non-numerical factors such as neighborhood name and school district.
Data Preprocessing:
-Adjust close prices of transactions based on market movement using the Zillow Home Price Index data.
-Modify sales prices to account for concessions, ensuring the adjusted sales price is used for testing and algorithm building.
Ranking and Comparison:
-Develop a system to compare a given property against all transactions over the prior year in a specific area, determining the property's rank among the set of transactions.
Confidence Scoring:
-Implement a feature to determine the confidence of the similarity scoring, allowing users to set a confidence threshold (e.g., 90%) and understand the ranking range (e.g., between the 15th and 21st sale).
Data Management:
-Work with data sets under 10,000 transactions, managing and preprocessing the data effectively for algorithm training and testing.
Collaboration and Innovation:
-Collaborate with the project team to identify valuable data points for the algorithm.
-Contribute innovative ideas for dynamically understanding and improving the accuracy of transaction similarity comparisons.
Qualifications:
-Proven experience in machine learning and algorithm development, specifically with boosted tree algorithms.
-Strong programming skills in relevant languages (e.g., Python, R).
-Experience in handling and analyzing large data sets, with a focus on real estate data being a plus.
-Ability to preprocess and analyze complex data, including adjusting for market movements and handling non-numerical data.
-Excellent problem-solving skills and creativity in developing innovative solutions.
-Strong communication skills for effective collaboration with the project team and clear presentation of ideas and progress.
This job is already closed and no longer accepting applicants, sorry.