Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195300,
        author = {Nayna Potdukhe and Isha Bhagat and Kaveri Agre and Palak meshram and Namrata Akmar},
        title = {Predicting Cultural Period of Archeological artifacts from digital heritage metadata by automated machine learning approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1797-1803},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195300},
        abstract = {Archaeological artifacts help us learn about the culture, history, and social life of ancient civilizations. Finding out the period of these artifacts is a key part of archaeology. It helps researchers understand how history unfolded, how cultures changed, and how technology developed in ancient societies. In the past, this type of classification was done by experts who looked closely at the features of the artifacts, like what they're made of, their design, how they're built, and where they were found. Even though this method works well, it can take a lot of time, require a lot of effort, and sometimes depend on personal opinions, especially when handling big groups of artifacts. As digital technology has improved, many museums, archives, and cultural places have created digital repositories that keep detailed information about archaeological items. This metadata could have details like what the object is made of, where it was found, the place where it was dug up, how it looks in terms of style, how old it is thought to be, and any records from history that are connected to it. Having access to structured and semi-structured data offers chances to use computer methods for automatic analysis and sorting. This study suggests a machine learning approach to predict the cultural time of archaeological items by using digital heritage information. The process includes different steps like preparing the data, finding important features, teaching the model, and checking how well it works. As we use various machine learning algorithms, such as KNN, Logistic Regression, Random Forest, SVM etc, machine learning algorithms look at patterns and connections in the metadata to help the system guess which cultural period an object is from. Our model achieves 98.9% accuracy on high-confidence predictions, covering 83.2% of artifacts, while flagging 15.2% for expert review–reducing manual workload by over 80%. It can help lower the amount of work people have to do by hand, reduce the chances of personal opinions affecting decisions, and make it easier to manage and find digital collections of historical value. Using machine learning with digital heritage data can help improve archaeological studies and support the protection and deeper understanding of cultural history.},
        keywords = {Logistics Regression, SVM, Random Forest, metadata, Artifact’s classification, Data Analysis, Heritage Repositories},
        month = {April},
        }