Adaptive kNN using Expected Accuracy for Classification of Geo-Spatial Data

TL;DR

This paper introduces an adaptive kNN classifier that dynamically selects the optimal number of neighbors for each data point based on expected accuracy, improving performance on geo-spatial datasets with irregular densities.

Contribution

It proposes a novel adaptive kNN method using expected accuracy and evaluates different similarity functions, outperforming existing kNN approaches on geo-spatial data.

Findings

Adaptive kNN outperforms standard kNN and previous adaptive methods.

Expected accuracy is a good estimator for kNN performance.

Range reduction of k speeds up the algorithm without accuracy loss.

Abstract

The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e.g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.