Predictive performance and farmer satisfaction of Jaɓnde, a digital decision-support tool for dairy-cow ration formulation: results from field assessment in Burkina Faso
Abstract
Background and objectives: Jaɓnde is a locally adapted ration formulation tool for resource-constrained dairy systems in sub-Saharan Africa. The version used in this study was the Excel-based prototype installed on a laptop. A mobile version, now available for free on the Google Play Store and online (https://jabnde.cirad.fr/), is under testing. This preliminary, supervised field validation pursued three objectives: (i) to compare the technical and economic performance of zebu and crossbred cows under dairy farmer-implemented rations; (ii) to assess the implementation fidelity and the predictive performance of Jaɓnde; and (iii) to assess dairy farmer satisfaction with the use of Jaɓnde. Methodology: The tool was tested by 40 volunteer dairy farmers in the Bobo-Dioulasso milkshed (Burkina Faso) on 82 lactating cows (65 zebu, 17 crossbred). Implementation fidelity was assessed from the mean difference (predicted ration, R2 -actual ration, R3), and predictive performance from robust linear regression, reported overall and by cow type using R², the slope, and error indicators (mean absolute error, MAE; root mean square error, RMSE; mean bias error, MBE), complemented by Bland-Altman analyses. A structured survey assessed the satisfaction of dairy farmers. Results: Dairy farmers implemented R3 ration close to R2 (mean differences -0.37 to +0.04 kg GM/cow/day across feed types). Predicted and actual values were strongly associated for most variables (R² > 0.70), though weaker for milk production among crossbred cows; bias remained limited (MBE = -0.27 L/d/cow for milk production). Agreement on milk production was the most independent performance indicator. Crossbred cows produced more milk (10.6 vs 1.2 L/d/cow), whereas the relative change was greater in zebu cows (33%vs 8% increase). Over 90% of dairy farmers reported increased production and were satisfied. Contributions: This first field assessment is encouraging: under supervised conditions, farmers implemented Jaɓnde's rations, predictive performance was promising for milk production, and satisfaction was high. Confirming its causal contribution and robustness will require controlled designs across more farms, seasons, and management systems.
Related
- Distinct amygdala-striatal and amygdala-cortical circuits encode and retrieve predictive learning to guide choice and decision-making
- Surfactant Compatibility Screening Improves Formulation Performance of Metarhizium anisopliae for Control of the Tomato Leafminer Phthorimaea absoluta
- Saccharin-Enabled Oral Formulation, Biopharmaceutics and Early Genotoxicity Assessment of the PPARγ Antagonist T0070907
- Perceived importance, self-rated performance satisfaction, learning stress, and practicum experiences among nursing students: A cross-sectional study with supplementary open-ended responses
- Functional and Structural Brain Age Gaps as Complementary Predictive Markers for Cognitive Performance
BibTeX
@article{ouattara2026predictive,
title = {{Predictive performance and farmer satisfaction of Jaɓnde, a digital decision-support tool for dairy-cow ration formulation: results from field assessment in Burkina Faso}},
author = {Songdah Désiré Ouattara and Ollo Sib and Mohamed Habibou Assouma and Souleymane Sanogo and Beh Traoré and Vinsoun Millogo and Valérie Marie Christiane Bougouma-Yaméogo and Eric Vall},
journal = {Veterinary and Animal Science},
year = {2026},
month = aug,
doi = {10.1016/j.vas.2026.100837},
url = {https://hal.inrae.fr/hal-05732611v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Predictive performance and farmer satisfaction of Jaɓnde, a digital decision-support tool for dairy-cow ration formulation: results from field assessment in Burkina Faso
AU - Songdah Désiré Ouattara
AU - Ollo Sib
AU - Mohamed Habibou Assouma
AU - Souleymane Sanogo
AU - Beh Traoré
AU - Vinsoun Millogo
AU - Valérie Marie Christiane Bougouma-Yaméogo
AU - Eric Vall
PY - 2026
DA - 2026/08/31
JO - Veterinary and Animal Science
DO - 10.1016/j.vas.2026.100837
UR - https://hal.inrae.fr/hal-05732611v1
AB - Background and objectives: Jaɓnde is a locally adapted ration formulation tool for resource-constrained dairy systems in sub-Saharan Africa. The version used in this study was the Excel-based prototype installed on a laptop. A mobile version, now available for free on the Google Play Store and online (https://jabnde.cirad.fr/), is under testing. This preliminary, supervised field validation pursued three objectives: (i) to compare the technical and economic performance of zebu and crossbred cows under dairy farmer-implemented rations; (ii) to assess the implementation fidelity and the predictive performance of Jaɓnde; and (iii) to assess dairy farmer satisfaction with the use of Jaɓnde. Methodology: The tool was tested by 40 volunteer dairy farmers in the Bobo-Dioulasso milkshed (Burkina Faso) on 82 lactating cows (65 zebu, 17 crossbred). Implementation fidelity was assessed from the mean difference (predicted ration, R2 -actual ration, R3), and predictive performance from robust linear regression, reported overall and by cow type using R², the slope, and error indicators (mean absolute error, MAE; root mean square error, RMSE; mean bias error, MBE), complemented by Bland-Altman analyses. A structured survey assessed the satisfaction of dairy farmers. Results: Dairy farmers implemented R3 ration close to R2 (mean differences -0.37 to +0.04 kg GM/cow/day across feed types). Predicted and actual values were strongly associated for most variables (R² > 0.70), though weaker for milk production among crossbred cows; bias remained limited (MBE = -0.27 L/d/cow for milk production). Agreement on milk production was the most independent performance indicator. Crossbred cows produced more milk (10.6 vs 1.2 L/d/cow), whereas the relative change was greater in zebu cows (33%vs 8% increase). Over 90% of dairy farmers reported increased production and were satisfied. Contributions: This first field assessment is encouraging: under supervised conditions, farmers implemented Jaɓnde's rations, predictive performance was promising for milk production, and satisfaction was high. Confirming its causal contribution and robustness will require controlled designs across more farms, seasons, and management systems.
SN - 2451-943X
ER -