Breast cancer is one of the leading diseases of death in women. It induces by a genetic mutation in breast cancer cells. Genetic testing has become popular to detect the mutation in genes but test cost is relatively expensive for several patients in developing countries like India. Genetic test takes between 2 and 4 weeks to decide the cancer. The time duration suffers the prognosis of genes because some patients have high rate of cancerous cell growth. We used a machine learning systems strategy that includes the extensive search for the discovery of the most optimal learning model, including feature selection algorithms, a feature extraction algorithm, and classifiers for diagnosing breast cancer. Hence, this study aims to obtain a high-importance transcript the profile linked with classification procedures that can facilitate the early detection of breast cancer. In the research work, a cost and time efficient method is proposed to predict the gene expression level on the basis of clinical outcomes of the patient by using machine learning techniques. An improved K Nearest Neighbour (KNN) with hyper parameter gene selection technique is proposed to find the most significant genes related to breast cancer afterward explained variance statistical analysis is applied to extract the genes contain high variance. The proposed method predicts the expression of significant genes with reduced Root Mean Square Error and acceptable adjusted R-square value. As per the study, analysis of these selected genes is beneficial to diagnose the breast cancer at prior stage in reduced cost and time.