Human lives are increasingly influenced by algorithms, which therefore need to meet higher standards not only in accuracy but also with respect to explainability. This is especially true for high-stakes areas such as real estate valuation, where algorithms decide over the price of one of the most valuable objects one can own. Unfortunately, the methods applied there often exhibit a trade-off between accuracy and explainability.On the one hand, there are explainable approaches such as case-based reasoning (CBR), where each decision is supported by specific previous cases. However, such methods are often wanting in accuracy. On the other hand, there are unexplainable machine learning approaches, which provide higher accuracy but are not scrutable in their decision-making.In this paper, we apply evolutionary algorithms (EAs) to close the performance gap between explainable and unexplainable approaches. They yield similarity functions (used in CBR to find comparable cases), which are fitted to the data set at hand. As a consequence, CBR achieves higher accuracy than state-of-the-art deep neural networks (DNNs), while maintaining its interpretability and explainability. This holds true even when we fit the neural network architecture to the data using evolutionary architecture search.These results stem from our empirical evaluation on a large data set of real estate offers from Japan, where we compare known similarity functions and DNN architectures with their EA-improved counterparts. In our testing, DNNs outperform previous CBR approaches. However, with the EA-learned similarity function CBR is even more accurate than DNNs.

No abstract