Background: Yam (Dioscorea alata L.) is the staple food of many populations in the intertropical zone, where it is grown. The lack of phenotyping methods for tuber quality has hindered the adoption of new genotypes from breeding programs. Recently, near‐infrared spectroscopy (NIRS) has been used as a reliable tool to characterize the chemical composition of the yam tuber. However, it failed to predict the amylose content, although this trait is strongly involved in the quality of the product.Results: This study used NIRS to predict the amylose content from 186 yam flour samples. Two calibration methods were developed and validated on an independent dataset: partial least squares (PLS) and convolutional neural networks (CNN). To evaluate final model performances, the coefficient of determination (R²), the root mean square error (RMSE), and the ratio of performance to deviation (RPD) were calculated using predictions on an independent validation dataset. The tested models showed contrasting performances (i.e., R² of 0.72 and 0.89, RMSE of 1.33 and 0.81, RPD of 2.13 and 3.49 respectively, for the PLS and the CNN model).Conclusion: According to the quality standard for NIRS model prediction used in food science, the PLS method proved unsuccessful (RPD < 3 and R² < 0.8) for predicting amylose content from yam flour but the CNN model proved to be reliable and efficient method. With the application of deep learning methods, this study established the proof of concept that amylose content, a key driver of yam textural quality and acceptance, can be predicted accurately using NIRS as a high throughput phenotyping method. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

In West and Central Africa and in the Caribbean, yam is one of the most important sources of carbohydrates and has a great potential to improve food security. The yam production sector is, however, now challenged by the satisfaction of evolving consumers' preferences. Since little is known about consumers' preferences regarding yams' characteristics, product quality, and the drivers of yam purchase, six focus group discussions were conducted (for a total of 31 participants). Among the purchasing criteria, price was considered more important than the others. It was followed by the external damage, the origin, and the size of the tuber. The most frequently cited consumption criteria were the taste, the texture, and color of flesh after cooking. Taste was considered more important than the other criteria. Three consumers' profiles were established reflecting heterogeneity in preferences, especially as concerns the willingness to pay for yam and consumption habits. They were designated as the Hedonistic, the Thrifty and the Flexible. Our results suggest that innovations can be implemented to sustain and stimulate the development of the yam sector in Guadeloupe. Two main development paths were identified. The first path is the valorization of the great existing diversity of yam varieties and the increase in the level of information for consumers about product attributes such as the cooking mode, the origin, and the mode of production. Building a marketing strategy based on the valorization of this diversity can help maintain and preserve yam's agro‐biodiversity and the satisfaction of rapidly evolving consumption habits. The second path is the definition of yam ideotypes that suit consumers' needs. We expect that tailoring the production to consumers' needs will have a positive impact on global food security in the Caribbean region.