It Takes a Family to Raise a (Digital) Village: Experimental Evidence with Coffee Farmers

The Digital Platform: The tool enables farmers to demonstrate compliance with EU deforestation regulations (e.g., EUDR). This is a powerful incentive for adoption as it directly links to market access and potentially higher prices.

Experimental groups:
We use a randomized controlled trial (RCT) in Antioquia, Colombia.
In the first stage, we will conduct a one-to-one baseline survey, which will allow us to characterize farmers' digital skills, agricultural practices, and socioeconomic conditions.
The farmers will be selected using the list of cooperative members of the association. Specifically, we will interview a sample of 1500 farmers from the association. The 150-minute survey will be conducted at farmers' houses. The visits will be pre-announced, and convenient times will be agreed upon. During the initial visit, participants will be informed about the project's objectives, the benefits they can expect, and how their data will be managed. Participants can withdraw from the project at any time without incurring any further consequences.
In the second stage, 1200 farmers will be randomized into the following five groups:
T1: Training App Platform - Individual: farmers interact with a trained peer extensionist who provides expert guidance on app usage and compliance practices.
T2: Training App Platform - Family: both the extensionist and a spouse or adult offspring of the farmer join the group
T3: Training App Platform - No Whatsapp group - Artificial Intelligence module
T4: App Platform no training - Individual
T5: App Platform no training - Family
T6: Pure Control Group: No app access no whatsapp
Farmers in T1 and T2 will participate in three one-day training sessions. The sessions will be conducted at a farm nearby, and transportation will be provided. The training sessions aim to prepare farmers for the use of sustainable agricultural practices following European Union Regulation on Deforestation-free Products (EUDR). The sessions use a participatory methodology where farmers learn practical skills in group activities. In the sessions, farmers discuss sustainable agricultural practices for the protection of soil, water, forest, and biodiversity. They learn how to document good practices using an App and practice commercialization and negotiation in different markets.
Farmers in T3: receive one session of practical training on the use of another app AI called "Croppie".
Farmers in T4 and T5: will have the option to install the App, but will not receive any type of agricultural training. They will not have access to "Croppie". This group is used as a reference to evaluate the impact of T1 to T3.
Farmers in T6 (Pure control group) will have access to the app one year later. The staggered implementation would allow us to validate the impact of the app without limiting the possibilities for the control group to benefit from it. This group works as a reference to evaluate the impacts of T3 and T4.
In the last stage, we will conduct a one-to-one end-line survey to evaluate the impact of the treatments and, in particular, T3. As before, the survey will be conducted at farmers' houses. The visits will be pre-announced and agreed upon. The impacts of the training program will be assessed at the household level by comparing the changes in digital adoption among farmers in the treated and control groups.

2025-10-01

2026-04-30

1. Digital adoption outcomes
1.1 App engagement: Number of compliance documents uploaded, Number of crop photos uploaded, Deforestation risk score generated from app use.
1.2. WhatsApp engagement: Volume and frequency of messages, Textual analysis of content (responsiveness, participation of farmer vs. family member), Group-level activity indicators (who replies, how quickly, how often).Platform Engagement: User logins, frequency of use, features accessed.
2. Compliance and sustainability outcomes
2.1. Improvement in compliance scores (Number and quality of pictures uploaded, algorithm-generated compliance score, personalized crop performance feedback.).
2.2. Adoption of recommended reforestation and best crop practices (as reflected in monitoring data).
3. Digital literacy (frequency of use of mobile phone (e.g. chat, listen music or watch tv, financial transactions, communication, etc.), perceived ability to handle different applications, perceived ability to acquire and select information, digital awareness and knowledge of different Apps.
4. Digital financial adoption

1. Financial inclusion outcomes
1.1.Savings behavior (changes in balances or frequency, use of precautionary savings, value of savings (formal and informal)).
1.2. Borrowing behavior (loan uptake, repayment, access to credit (extensive and intensive margins)).
1.3. Insurance: access to crop insurances and other social protection mechanisms and value of assets. This includes titles over properties and estimated value of assets (land, vehicles, machines and other assets)
1.4. Investment: Investment in coffee cultivation considers the extent and the value invested in coffee production. This include investment in labor and capital. We also construct a measure on the use of more sustainable practices in the coffee cultivation (use of organic fertilizer, efficient water use, recycling of material)
1.5. Indicators linking digital adoption to digital financial inclusion (Use of digital financial apps)

2. Income
2.1. Annual Income
2.2 Relative wealth
2.3. Financial literacy

3. Others
3.1 Agricultural entrepreneurial image
3.2 Resilience capacity
3.3. Marketing strategies
3.4. Risk and time preferences

Agricultural entrepreneurial image is a perception measure on willingness to innovate, take risk and lead the community. Questions are normalized so a higher value indicates more entrepreneurial skills.
Resilience capacity is a indicator of the perception on the ability to cope with difficulties and stress.
Marketing strategies consider the transformation to higher value added in coffee production chain by delivering a more elaborated product (e.g. class A dry coffee) or accessing new markets.
Trust in local organization. We measure trust in coffee cooperative, local administration, national government and police.
Risk aversion, patience, impulsiveness combine self-reported measures in a 1-10 scale with behavioral question on hypothetical scenarios that imply intertemporal decisions or risky investments. The measures are not incentivized.

The experimental design uses a between subject design. Based on baseline characteristics of the population, we create 5 treatment groups and a control group. The groups vary the access to a mobile App to document agricultural practices (access vs. no access), the modules included in the app (Al Invest vs Croppie) and the type of training (farmer alone or farmer with family member).
T1: Access to the APP, NO access to Croppie, training on basic modules AL invest, WhatsApp with farmer only
T2: Access to the APP, NO access to Croppie, training on basic modules AL invest, WhatsApp with farmer + family member
T3: Access to Croppie, training on Croppie module only, NO WhatsApp
T4: Access to the APP, NO access to Croppie, no training, WhatsApp with farmer only
T5: Access to the APP, NO access to Croppie, no training, WhatsApp with farmer + family member
T6: Pure control: No Access to the APP, NO access to Croppie, no training

Not available

The randomization is done applying the Mean Squared Error (MSE) approach developed by Schneider (2021). The method uses baseline sample characteristics to obtain balanced treatment groups by an interactive process that forms groups such that it minimized the mean squared error of the baseline observable characteristics. Link:
https://www.sebastianoschneider.com/publication/schneider-schlather-2021/

The unit of randomization is the individual.

No

1200 farmers

1200 farmers

T1: 150
T2: 150
T3: 300
T4: 150
T5: 150
T6: 300

The Minimum Detectable Effect size is 0.3 standard deviations, considering a take-up of 80 percent, an attrition level of 5 percent, and a power of 0.8 with a 5 percent significance level