• Shivani Shitole
• Prof. Sachin Dada Shinde
• Dr. Rahat Khan

The K-Nearest Neighbors (KNN) algorithm is a straightforward, flexible method used for both classification and regression tasks in machine learning. It works by predicting the label or value of a data point based on the labels or values of its closest neighbors in the data. In classification, KNN looks at the labels of the k nearest neighbors of a given point and assigns the most common label among them. In regression, it predicts the value by averaging the values of the k nearest neighbors. One of the key features of KNN is that it doesn’t make assumptions about the underlying data (this is called "non-parametric"), and it doesn't build an explicit model during training ("lazy learning"). Instead, it simply stores all the data and makes predictions when it needs to, by comparing new points to the stored data. However, KNN’s performance depends on a few factors: the number of neighbors (k) chosen, the distance metric used to measure similarity (such as Euclidean distance), and the scale of the data features. While KNN can be slow and computationally expensive, especially with large datasets, it’s easy to implement and works well for problems where the decision boundaries are complex or not linear. It’s a useful algorithm for many practical applications despite its computational drawbacks.

KNN algorithm, Supervised learning, AI (Artificial Intelligence), Ecommerce, Recommendation, ML (Machine Learning).

"AI-Powered Social Media Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 8, page no.74-77, August-2025, Available :http://www.jetir.org/papers/JETIRHA06012.pdf

"AI-Powered Social Media Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 8, page no. pp74-77, August-2025, Available at : http://www.jetir.org/papers/JETIRHA06012.pdf