The advent of data-intensive services needs quality Internet services. This in turn, makes Qualityrnof Experience (QoE) gain prominent recognition in the telecommunications industry. Ethio telecomrnuses network Quality of Service (QoS) monitoring data obtained from Network ManagementrnSystems (NMS) tools to comprehend its network performances. However, as QoS measurementrnrefers to network performances, this method does not generally give QoE data as perceivedrnby the user. Therefore, QoE estimation models are proposed as solutions in the literature,rnrecently.rnThis study focuses on developing QoE estimation models using QoS features of round-trip timern(RTT), jitter, loss rate (LR) and throughput, and QoE scores collected using Application for prediCtingrnQUality of experience at Interne Access (ACQUA)-based crowdsourcing in UniversalrnMobile Telecommunication Systems (UMTS) networks in a real-time basis. Data preparationsrntechniques such as data cleaning and dataset imbalance corrections have been applied to therncollected datasets. Machine Learning (ML) algorithms of Arti cial Neural Network (ANN), KNearestrnNeighbor (KNN) and Random Forest (RF) are selected based on their suitability for multilabelrnproblems. After training these models developed, they are evaluated using commonly usedrnperformance metrics such as accuracy, Root Mean Square Error (RMSE) and Receiver OperatingrnCharacteristics (ROC).rnExperimentation results exhibit that RF with an accuracy of 98.39%, is the best model whilernKNN and ANN achieve 87.47% and 77.59% overall accuracy, respectively. As a conclusion, allrnthree models achieve acceptable performances. As a conclusion, our QoE estimation models ifrnimplemented can help Telecommunications Service Providers (TSP) in estimating user QoE inrnreal-time.