Classical Computing (CC) takes place in the binary form of 0 and 1, whereas Quantum Computing (QC) takes place adhering to fundamental principles of quantum mechanics, i.e., superposition, entanglement, and tunneling. Humanity is in the race to show that QC is better than CC in terms of time, accuracy, and memory requirements. But since Fault-Tolerant QC hardware with solving problems computationally exhaustive for today’s CC are out of reach, we in this paper emulate Use case of the Recommendation System on Quantum Singular Value Transform Framework (QSVT) of Quantum-Inspired Machine Learning (QiML) on CPU using the Qiskit Library, pyqsp library and have shown a quantum advantage in terms of accuracy, in terms of time and memory requirement classical implementation is a winner as computations in the Quantum Emulations are larger owing to unitary matrix conversions of input matrix and considerable depths, but these depths can be reduced to approximate the target polynomial function in which case the Quantum Implementation is comparable to/better than its counterpart at cost of accuracy.The entanglement principle of QM is used in the QSVT Circuit for entangling the QSVT Qubit with unitary Qubits by using the CNOT gates. Also, the entanglement principle is inherently present in the Input User Preference Rating Unitary Matrix as well, if the exact tensor decomposition at a break-off qubit length of the input user preference unitary matrix is not possible.The input quantum state of our QSVT circuit can be initialized to the superposition of input user states to access all the items corresponding to all the users in one run of the circuit. Hence by using the fundamental principles of quantum mechanics, we have shown quantum advantage over classical implementation in terms of accuracy.