International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 11 Issue: 1s DOI: https://doi.org/10.17762/ijritcc.v11i1s.5991 Article Received: 05 November 2022 Revised: 18 December 2022 Accepted: 20 December 2022 ___________________________________________________________________________________________________________________ 23 IJRITCC | January 2023, Available @ http://www.ijritcc.org I. INTRODUCTION The learning models were used to assess the health data to identify health risks, as large-scale, high-dimensional (HD) datasets have currently been available across a variety of fields and technologies [1]. One of the key causes of breast cancer (BC) death as well as one of the major worldwide health issues [2]. The most common cancer is breast cancer which is presented in females, and one of the killers of females [3]. According to the WHO, three out of every 10 females who received a BC diagnosis worldwide passed away in 2020 [4]. Due to its stealthy progression, the majority of BC diseases are found during routine screening [5]. BC incidence, mortality, and survival rates may be impacted by several variables, including the environment, genetics, way of life, and population structure [6]. When BC is found early and treated, the chance of survival is very good [7]. BC is affected by two main factors modifiable and non- modifiable. The modifiable factors (MF) are individuals that can be managed, such as environmental problems and behaviors, and other type factors are those that can’t be addressed, such as gender and personal history [8]. According to a review, one out of twenty-eight females across India is Machine Learning-Based Hybrid Recommendation (SVOF-KNN) Model For Breast Cancer Coimbra Dataset Diagnosis Ravi Kumar Barwal 1 , Dr Neeraj Raheja 2 , Dr. Malika Bhiyana 3 , Dimple Rani 4 1 Department of Computer Science and Engineering, Maharishi Markandeshwar Engineering College Maharishi Markandeshwar (Deemed to be University), Mullana, Ambala, Haryana, India barwal606@gmail.com 2 Department of Computer Science and Engineering, Maharishi Markandeshwar Engineering College Maharishi Markandeshwar (Deemed to be University), Mullana, Ambala, Haryana, India neeraj_raheja2003@mmumullana.org 3 Govt P.G College, Ambala Cantt, Haryana, India malikabhiyana@gmail.com 4 Govt P.G College, Ambala Cantt, Haryana, India dimplemehra7@gmail.com Abstract— An effective way to identify breast cancer is by creating a prediction algorithm using risk factors. Models for ML have been used to improve the effectiveness of early detection. This article analyses a KNN combined with singular value decomposition and Grey wolf optimization(GWO) method to give a detection of breast cancer(BC) at the early phase depending on risk metrics. The SVD technique was utilized to eliminate the reliable feature vectors, the GW optimizer was used to select the feature vectors, and while KNN model was used to diagnose the BC status. The proposed hybrid recommendation model (SVOF-KNN) for BC prediction's main objective is to give an accurate recommendation for BC prognosis through four different steps such as;BCCD dataset collection, data pre-processing, feature selection, and classification/recommendation. It is implemented to classify the consequence of risk metrics connected withregular blood analysis(BA) in the BCCD database. The aspects of the BC dataset are insulin, glucose, HOMA, Leptin, resistin, etc. The error categories such as RMSE and MAE are used to calculate the exception values for each instance of the BC dataset. It hybrid model has recommended the best score instance having the minimumexception rateas the defined features for BC prediction. It improves significance in automatic BC classification with the optimum solution. The hybrid recommendation model (SVOF-KNN) also recommends the accurateclassification method for BC diagnosis. The results of this work shall enhance the QoS in BC care. Keywords- HRS (healthcare recommendation system); ML (Machine learning); SVOF-KNN model; SVD (singular value decomposition) feature extraction; GWO (grey wolf optimization)feature selection; BCCD (breast cancer coimbra dataset); MAE (means absolute error), RMSE (root means square error).