Point of Sale Satisfaction Analyzer

Sentiment Analysis is already widely used by different companies to gauge consumer mood towards their product or brand in the digital world. However, in offline world users are also interacting with the brands and products in retail stores, showrooms, etc. and solutions to measure user’s reaction automatically under such settings has remained a challenging task. Emotion Detection from facial expressions using Deep Learning algorithms can be a viable add-on to automatically measure consumer engagement with their content and brands.

Problem Statement: Our team worked with one of the largest retail coffee chain in the U.S. with the aim to improve understanding of the in-store customer experience by analyzing customer sentiment and emotions.

Approach: Using captemo™ cloud-based AI solution, we executed the project to detect, measure and analyze the most transitory of facial expressions, such as happiness, anger, and surprises. Additionally, we have assimilated emotions data with other key internal and external data sources such as sales, employee, weather to provide valuable business insights.

Outcome: Business is able to develop and monitor new key performance indicators (KPIs) which is based on customer emotional sentiments such as “Customer Happiness Index” by day, time of the day, employee shift time, etc. and evaluate strategies to consistently promote customer experience and excellence program.

Training Program Effectiveness Score

Problem Statement: Our team engaged by one of the big 4 consulting firm to evaluate the effectiveness of the trainings conducted by vendors for their employees.

Approach: Using captemo™ cloud-based AI solution, we have examined whether facial expression of the participants is a tool for the trainer or facilitator to interpret comprehension level of participants in a physical classroom environment, and also to identify the impact of facial expressions during the training session and the level of comprehension shown by these facial expressions.

Outcome: The analysis was done through face detection and recognition techniques, which includes the recording of participant’s behaviors at defined interval through the training session. The result shows that facial expression is the most frequently used nonverbal communication mode by the participants, and it is significantly correlated to their emotions which helps to recognize their comprehension towards the session and evaluate the effectiveness score of the overall training program.

Making Cars Safer and more Personalized

Problem Statement: Car Manufacturers around the world are increasingly focusing on making cars safer and more personal for us to drive. In their pursuit to build more smart car features, it makes sense for makers to use AI to help them understand the human emotions. Using facial emotion detection smart cars can alert the driver when he is feeling drowsy.

Approach: Facial emotion detection can find subtle changes in facial micro-expressions that precedes drowsiness and send personalized alerts to the driver asking him to stop for a coffee break, change music or temperature.

Additional value-added insights: Facial expressions can help the sales associates to assess the customer experience while providing demo of features, during the test drive, and use to improve on customer service protocols.