Background: Accurate evaluation of the response to neoadjuvant chemotherapy (NAC) provides important information about systemic therapies for breast cancer, which implies tumor biology, prognosis, and guide further therapy. Gene profiles overcome many limitations observed with classic histopathological variables but are complicated and expensive. Therefore, it is essential to develop a more accurate, repeatable, and economical evaluation approach for neoadjuvant chemotherapy responses. Methods: We analyzed the transcriptional profiles of chemo-resistant breast cancer cell lines and tumors of chemo-resistant breast cancer patients in the GEO25066 dataset. We preliminarily screened out common significantly differentially expressed genes and constructed a NAC response risk model using least absolute shrinkage and selection operator (LASSO) regression and univariate and multivariate analyses. The differences in prognosis, clinical features, tumor microenvironment components, and immune characteristics were compared between risk groups. The connectivity map (CMap) database was used to screen potential drugs that could reverse chemotherapy resistance in breast cancer. Results: Thirty-six genes were commonly overexpressed or downregulated in both NAC chemo-resistant tumors and cells compared to the sensitive tumors and wild-type cells. Through LASSO regression, we obtained a risk model composed of 12 genes. The risk model divided patients into high-risk and low-risk groups. Univariate and multivariate Cox regression analyses indicated that the risk score can be used as an independent prognostic factor for evaluating NAC response in breast cancer. Tumors in the high-risk and low-risk groups showed significant differences in molecular biological characteristics, tumor-infiltrating lymphocytes, and immunosuppressive molecule expression. Our results showed that the risk score was also an independent prognostic factor for breast cancer. Finally, we screened potential drugs that could reverse chemotherapy resistance in breast cancer. Conclusion: Our results suggest that the novel signature of 12 genes could be used to evaluate NAC response and predict prognosis in breast cancer.