• Vikram K N
• Elaiyaraja P
• Monisha P
• Pooja
• Shamanth

Imbalanced information classification issue has continuously been a well known theme within the field of machine learning investigate. In arrange to adjust the tests between larger part and minority course. Oversampling calculation is utilized to synthesize unused minority course tests, but it seem bring in commotion. Indicating to the noise issues, this paper proposed a denoising autoencoder neural organize (DAE) calculation which cannot as it were oversample minority course test through misclassification taken a toll, but it can denoise and classify the examined dataset. Through tests, compared with the denoising autoencoder neural arrange (DAE) with oversampling handle and conventional completely associated neural systems, the comes about appeared the proposed calculation progresses the classification exactness of minority lesson of imbalanced datasets.

Imbalanced data; Oversampling; Denoising autoencoder neural network; Classification

"Autoencoder Transaction Evaluation ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.g427-g433, May-2024, Available :http://www.jetir.org/papers/JETIR2405652.pdf

"Autoencoder Transaction Evaluation ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppg427-g433, May-2024, Available at : http://www.jetir.org/papers/JETIR2405652.pdf