Method of Generating Real-Time Digital Customer Feedback Loop for Connected Vehicle Applications.

Modern cars are essentially computers on wheels in terms of the technology stack going into the car. Similarly, the customer experience is gone beyond the conventional touch and feel to more digital experiences around the car. While creating digital experiments around the car, getting honest customer feedback on the same is essential. Getting customer feedback in real-time and at scale is a challenge. Generally, this is limited to surveys and campaigns OEMs do to collect specific intent. In this paper, we propose a method of generating a real-time customer digital feedback loop. This method relay on real-time sourcing of data from openly available sources like Twitter, mobile app stores, etc. The real-time collected data is run through an analytics system. The analytics system contains four key stages, data preparation, sentiment segmentation, topic modelling and inference presentation. This paper in detail covers advanced machine learning techniques like natural language processing using LSTM models, sentimental analysis using foundational models, and custom topic modelling for mapping the feedback with connected car features. The analytics system enables us to get an overall experience of the vehicle experience. In addition, topic modelling techniques help to get the user feedback localized to features. In this paper, we focus on the feature that is part of connected car apps. This paper covers the limitations of the system like the data imbalance due to more negative customer feedback. Detailed results and future scope will be part of the conclusion section of this paper.