The Applied Data Science Track solicits submissions that present compelling applications of Knowledge Discovery, Data Mining, and Machine Learning to solve challenging and important real-world problems, thereby bridging the gap between practice and theory. The submitted papers should clearly explain the specific real-world challenges addressed (encompassing aspects such as size, data quality, and evaluation), the methodology used, and the conclusions and implications that are drawn for the respective use cases.

The ADS track aims to accept papers that provide practitioners with valuable insights into how to apply Knowledge Discovery, Data Mining, and Machine Learning in real-world scenarios, showcasing their practical relevance. Alternatively, submissions may highlight novel use cases that contribute to expanding the understanding of the applicability of these methodologies in practical settings. Lastly, the track welcomes papers contributing to the overall knowledge base on the real-world application of Knowledge Discovery, Data Mining, or Machine Learning. The long-term impact on the community is the main criterion considered in the evaluation process.

Although not mandatory, authors are encouraged to comment on the deployment goals of their solutions and provide relevant details regarding deployment status and plans. In this context, deployment refers to the practical implementation or application of the proposed solutions in real-world scenarios. The track acknowledges that not all papers may present a deployed solution but emphasises the importance of explicitly discussing deployment in a realistic and transparent way.

Regarding methodological novelty, this track does not require the introduction of novel techniques. Instead, the emphasis is placed on the relevance and impact of the applied solutions to real-world challenges, even if proposed systems combine previously known building blocks. Authors are encouraged to focus on their work's practical implications and significance rather than on introducing novel methodologies.

Finally, the use of proprietary data is acceptable. However, it is expected that at least some portion of the data be made public, or a public dataset is also used to facilitate transparency and reproducibility.