Data is composed of actual data that translates to a sequence that can be processed by the machine. Data can be analysed and used to enhance the revenue of the company, to create a new chemical formulation, to make unique applications and to aid in the establishment of innovative modes of communication. The key element of work for any industry is to analyse the data acquired and adapt trends or achieve economic insights to tackle any given problem. The analysis of data is as qualitative as the accuracy of the information. The data obtained should be accurate and consistent. Improper data collection may lead to incorrect data visualizations resulting to inaccurate analysis and erroneous results. Most industries aim for accuracy and better performance where a tiny mistake may lead to heavy losses. In this condition, the incorrect decisions taken due to improper data analysis may lead to crucial circumstances. In this work, we propose a hybrid model which is the combination of long short-term memory (LSTM) and recurrent neural network (RNN) for detecting the anomalies or abnormalities in the data during the request raised by the customer. The proposed model is found to be even more efficient in identifying an anomaly in the data collection, taking into consideration of date and time constraints. The proposed model delivered enhanced performance compared to other traditional approaches.