Data25taco

Our research paper, “TACO: A Lightweight Tree-based Approximate Compression Method for Time Series”, has been accepted for presentation at the 14th International Conference on Data Science, Technology and Applications, DATA (DATA 2025). As time series data is growing, storage and transmission are major challenges. We present TACO: a fast, training-free, tree-based compression method. In comparision to the state-of-the-art, it has no strong assumptions and offers selective decompression.