Distributed Denial of Service (DDOS) in IOT based systems has become a vital consideration especially since the quintessential development of IOT based gadgets including small Personal Digital Assistants (PDA) to large computing systems. The stupendous and prolonged presence of such innovations have attracted potential attackers, encouraging them to carry out cyber-attacks and data theft. The key objective of this research is to detect and mitigate botnet-based distributed denial of service (DDoS) attacks in IoT networks. Our proposed model addresses the issue concerning threats from bots. Multiple machine learning models such as K-Nearest Neighbour (KNN), K-Means clustering, Fuzzy clustering and Deep learning models such as Conventional Neural Network (CNN), Recurrent Neural Network (RNN) Long Short Term Memory (LSTM) were used to arrive at the model, wherein the model is trained by Bot-Iot dataset. Various preprocessing methods were equipped and Performance-based selection was done to choose algorithms from a collection using the reference point, (i.e) accuracy percentage. Feature selection and Synthetic minority oversampling technique (SMOTE) were also incorporated alongside Machine Learning (ML) algorithms. The results of the model indicates that the proposed architecture can effectively detect botnet-based attacks and also can be extended with corresponding architectures for unfolding attacks.