ISSN: 2320-5407 Int. J. Adv. Res.

12(09), 1444-1453

Journal Homepage: - www.journalijar.com

Article DOI: 10.21474/IJAR01/19581

DOI URL: http://dx.doi.org/10.21474/IJAR01/19581

RESEARCH ARTICLE
AGRARIAN. AI

Amith R., Hetal Rakesh Lad, J.M Suhas and Jalla Sai Swetha
Student, Department of Computer Science and Engineering, BMS Institute of Tecnology and Management.
……………………………………………………………………………………………………....
Manuscript Info Abstract
……………………. ………………………………………………………………
Manuscript History For the agriculture industry to remain sustainable, it needs to improve
Received: 30 July 2024 output, quality, marketing infrastructure, and food management. Supply
Final Accepted: 31 August 2024 chain transparency is required due to food safety concerns, and
Published: September 2024 traceability technologies such as blockchain and AI are essential for
confirming the provenance of products. Significant improvements to
Key words:-
Agriculture Sustainability, Supply Chain the agricultural system are required to meet growing demand.
Transparency, Modern Agricultural Blockchain and artificial intelligence (AI) are two examples of modern
Solutions, Traceability Technologies, technologies that are essential for solving difficult problems and
Blockchain, Artificial Intelligence (AI)
expediting procedures. In order to advance agriculture toward a more
transparent, safe, and sustainable future, this abstract highlight the
significance of technology.

Copyright, IJAR, 2024,. All rights reserved.

……………………………………………………………………………………………………....
Introduction:-
The agriculture industry has seen a shift in recent years toward using technologies to address persistent issues like
supply chain transparency and market price volatility. Blockchain technology and artificial intelligence, especially
algorithms like Random Forest and Support Vector Machine are two of the most exciting new developments in this
field. This introduction explains how blockchain technology combined with artificial intelligence and sophisticated
algorithms is transforming agriculture through improved transparency and precise price prediction.

The agricultural supply chain has been facing a lot of inefficiencies with stakeholders battling with incomplete and
asymmetric information. Farmers frequently have no idea how their produce gets from the farm to the market, and
consumers have trouble confirming the legitimacy of agricultural goods. Furthermore, farmers face substantial
difficulties in scheduling their output and obtaining fair prices for their products due to price volatility and shifting
market dynamics.

An answer to these problems is provided by blockchain technology, which gives agricultural supply chains
transparency, traceability, and immutability. All of the supply chain's transactions and data points are safely and
openly recorded thanks to blockchain's decentralized ledger technology. This guarantees authenticity, standard
compliance, and ethical sourcing practices by allowing stakeholders to follow the provenance and journey of
agricultural products in real-time. Blockchain improves transparency from farm to fork in the agricultural value
chain by promoting trust and accountability.

Artificial intelligence contains complex algorithms like Random Forest and Support Vector Machine, enhances
blockchain's transparency initiatives by providing strong tools for evaluating enormous volumes of data and
producing precise forecasts. Combining the results of several decision trees, Random Forest is an ensemble learning
algorithm that performs exceptionally well with massive datasets and prediction-making. On the other hand, Support

Corresponding Author:- Amith R. 1444

Address:- Student, Department of Computer Science and Engineering, BMS Institute of
Tecnology and Management.
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

Vector Machine is well known for its capacity to identify the best hyperplane in high-dimensional space to divide
data points into distinct categories.

When these AI algorithms are used in agriculture, they can accurately predict prices by analysing a variety of
datasets that include variables like supply chain dynamics, weather patterns, market demand, and geopolitical
events. Random Forest and Support Vector Machine algorithms are able to predict market trends and price
fluctuations with remarkable accuracy by learning from past data and identifying patterns. This gives farmers and
traders important information about how prices will move in the future, empowering them to take well-informed
decisions and successfully manage risk. With the help of algorithms like Random Forest and Support Vector
Machine, blockchain technology and artificial intelligence can be combined to create a more transparent, effective,
and sustainable agriculture sector. These technologies enable stakeholders to navigate uncertainty more skillfully,
optimize production strategies, and promote equitable trading practices by giving them real-time visibility into
supply chains and predictive insights into market prices. With an emphasis on improving transparency and
facilitating precise price prediction, we explore the uses, advantages, and difficulties of fusing blockchain
technology with artificial intelligence in agriculture.

Literature Survey:-
"Agri-4-All: A Framework for Blockchain Based Agricultural Food Supply Chains in the Era of Fourth Industrial
Revolution," IEEE Access.

This paper offers a comprehensive examination of the fusion between blockchain technology and the Internet of
Things (IoT) within the realm of smart agriculture. Beginning with a systematic survey and bibliometric analysis, it
navigates through the challenges faced by Indian farmers, setting clear research objectives. A unique blockchain
model is proposed to tackle critical hurdles in IoT-based smart agricultural systems. Through a thorough evaluation,
the study highlights the pivotal roles and strengths of prevalent blockchain platforms in managing diverse facets of
smart agriculture, ranging from crop cultivation to livestock management and food supply chain logistics. It
categorizes the potential applications of blockchain in agriculture, encompassing crop production, food safety
enhancement, weather crisis management, food supply chain optimization, and equitable payment systems for
farmers. This insightful analysis underscores the transformative potential of blockchain technology in
revolutionizing agricultural practices, paving the way for enhanced efficiency, transparency, and sustainability
throughout the agricultural value chain.

"Blockchain Technology to Support Agri-Food Supply Chains: A Comprehensive Review," IEEE Access.

The paper undertakes a thorough investigation into the utilization of blockchain technology in agriculture,
employing a methodology that integrates literature review, case study analysis, and expert consultation. It delves
into the technical aspects of blockchain, including data storage mechanisms, cryptographic techniques, consensus
protocols, and the process of blockchain data generation. Moreover, the paper categorizes and evaluates existing
agricultural blockchain applications, highlighting their diverse uses and implications within the sector. It also
identifies key challenges encountered by blockchain implementations in agriculture, such as scalability issues,
integration complexities, and security concerns, and proposes potential solutions based on expert insights and
analysis. Through this multifaceted approach, the paper aims to provide a comprehensive understanding of
blockchain's applicability in agriculture and offer actionable insightsto address challenges and promote the adoption
ofblockchain solutions in the industry.

"Price Prediction Model of fruits, Vegetables and Pulses according to Weather," 2023 13th International Conference
on Cloud Computing, Data Science & Engineering (Confluence)

The paper explores the integration of blockchain technology and smart contracts into agricultural supply chains to
enhance traceability, transparency, and efficiency. It underscores the pressing need for robust traceability solutions
to tackle food safety and corruption concerns in these supply chains. Blockchain emerges as a revolutionary tool for
ensuring commodity traceability, offering immutable transaction records across the supply chain. The proposed
framework capitalizes on blockchain to monitor crop prices and ensure traceability throughout the agricultural
supply chain. By eliminating the reliance on trusted intermediaries, the system promises transparent, secure, and
efficient transactions. It delineates four pivotal phases: Farmer, Dealer, Sub Dealer, and Customer, each contributing
to the integrity and reliability of the supply chain. Additionally, the methodology entails employing cryptographic

1445
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

hash functions like SHA-256 for data integrity and security. The paper concludes by highlighting blockchain's
potential to address challenges in agricultural supply chains and outlines future research directions, including the use
of cryptocurrencies and smart contracts for automated payments and delivery proof, thus aiming to foster effective
physical plant and product distribution.

"Blockchain Technology in Agriculture for Indian Farmers: A Systematic Literature Review, Challenges, and
Solutions," in IEEE Systems.

The paper explores the integration of blockchain, smart contracts, and the Internet of Things (IoT) in agricultural
supply chains, crucial for Industry 4.0 business process re-engineering. It investigates their role in automating
processes, real-time monitoring, and transaction security within the agricultural sector. Employing Business Process
Modeling (BPM), the study critically assesses the relevance of these technologies across various agricultural supply
chain activities. Findings from BPM, focusing on intra- and inter-organizational processes, are integrated into the
Reference Architecture for Modeling Industry 4.0 (RAMI 4.0). This integration leads to the development of Agri-4-
All, a framework for smart agriculture supply chains, facilitating process automation within and between
organizations. The study develops, deploys, and tests smart contracts using the Solidity language, showcasing a
significant reduction in gas costs through hybrid smart algorithms. Methodologically, the paper employs BPMN
models to capture agricultural supply chain processes, highlighting the potential roles of IoT, blockchain, and smart
contracts. Mapped information is aligned with RAMI 4.0's layers, hierarchy levels, and product life cycle & value
stream. The proposed framework enhances supply chain transparency, efficiency, and customer visibility, albeit with
limitations regarding interoperability and privacy. Future work aims to address these challenges for a more
comprehensive framework.

"A Methodology for Crop Price Prediction Using Machine Learning," 2022 IEEE 2nd International Conference on
Mobile Networks and Wireless Communications (ICMNWC)

The paper explores the transformative impact of blockchain technology on agri-food supply chains, filling a gap in
existing literature by providing a comprehensive analysis of its application in this sector. Through a thorough
examination of 183 papers and addressing six research questions, the study elucidates both the benefits and
challenges of integrating blockchain into agri-food supply chains. Blockchain's unique features, including
transparency and immutability, make it ideally suited for enhancing traceability within these supply chains, enabling
stakeholders to track products from production to distribution with unparalleled reliability and trust. Proposed
architectures typically involve various actors such as producers, distributors, retailers, and end consumers, each
playing a vital role in the decentralized network. Smart contracts ensure data accuracy, while IoT sensors contribute
real-time data, further enhancing the system's resilience. Despite growing interest, industry participation in
blockchain deployment remains limited, underscoring the need for expanded training, integration of complementary
technologies like Big Data and Edge Computing, and the development of supportive tools for developers to fully
leverage blockchain's potential in agrifood supply chains.

"Enhanced Crop Price Prediction & Forecasting System," 2022 International Conference on Computer, Power and
Communications (ICCPC)

The paper discusses the pressing need for technological advancements in agriculture to tackle issues like yield
recommendations and crop price forecasting. It highlights the potential of modern technologies, particularly machine
learning (ML) models like decision trees and neuroevolutionary algorithms, in enhancing crop productivity and
pricing estimates. Through a thorough analysis of ML techniques in agriculture, the paper showcases the
effectiveness of these models in providing accurate predictions. The proposed framework utilizes regression models,
K-nearest neighbor (KNN) algorithms, support vector machines (SVM), decision trees, random forests, and artificial
neural networks (ANNs) to predict crop yields and prices efficiently. Additionally, deep learning techniques such as
convolutional neural networks (CNNs) and long short-term memory (LSTM) networks are explored for their
potential in timeseries forecasting and sequence data analysis. The study also evaluates various performance metrics
of the proposed models, including mean absolute percentage error (MAPE), mean absolute error (MAE),
determination coefficient (R-squared), root mean square error (RMSE), and mean squared error (MSE),
demonstrating the robustness and accuracy of the framework. The paper concludes by emphasizing the importance
of integrating advanced technologies into agriculture to meet the demands of a growing global population, proposing

1446
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

future research directions, including the development of automated crop yield and price recommendation systems
using genetic algorithms.

"Block chain Technology in Agriculture Product Supply Chain," 2021 International Conference on Artificial
Intelligence and Smart Systems (ICAIS)

The paper proposes the use of machine learning (ML) algorithms for agriculture price prediction, particularly
relevant for economies like India with a significant agricultural sector. Focusing on commodities like rice, wheat,
milk, and fruits such as mangoes, the study utilizes datasets from NAFHA to forecast prices based on five years of
historical data. Advanced statistical techniques like naive Bayes improve clustering algorithm accuracy, achieving
an impressive 85% correct predictions. The Random Forest Algorithm is employed to handle dynamic raw data,
considering environmental and climatic factors. Preprocessing steps involve using Decision Tree and Support
Vector Machine to make the data more amenable to algorithm application, ensuring higher accuracy. The process
includes collecting and processing dynamic raw data, feature extraction, and classification. Trained and test datasets
are compared using SVM, with results verified against real-time field data. Python is chosen as the primary
programming language for its versatility in data science tasks. The results showcase the potential of ML in
agriculture price prediction, offering precise forecasts with minimal computational resources, and hint at future
applications in big data for price forecasting. The study emphasizes the urgency of addressing agricultural pricing
challenges and concludes by presenting predictive price results for agricultural products.

"Blockchain Technology in Current Agricultural Systems: From Techniques to Applications," in IEEE Access.

The paper addresses the intersection of two significant domains: speech recognition technology and agriculture in
India. It discusses the prevalence of speech recognition systems like Amazon Alexa and Siri and their potential
utility in providing support to farmers. In India, where agriculture is a cornerstone of the economy, there's a crucial
need for better information and assistance for farmers, particularly in regional languages. While current methods of
price prediction for agricultural commodities rely on short-term arrivals and historical data, they often lack
comprehensive recommendations for farmers. The study aims to bridge this gap by developing a crop
recommendation system based on price forecasting, offering valuable advisories to farmers to help them make
informed decisions about storage and sales options. By leveraging artificial intelligence and machine learning
techniques, the study seeks to enhance existing frameworks and consider broader socio-economic factors such as
government policies and cultural events in predicting agricultural commodity prices. Ultimately, the goal is to
empower farmers with the tools they need to maximize profits and improve agricultural productivity in India.

"A Study on Agriculture Commodities Price Prediction and Forecasting," 2020 International Conference on Smart
Technologies in Computing, Electrical and Electronics (ICSTCEE).

The paper discusses the significance of tracking and forecasting market prices for agricultural crops, crucial for
effective Agri-management. It emphasizes the establishment of an official website by the Council of Agriculture
(COA) in Taiwan, providing open data on daily market prices for over 100 different crops from 15 local markets.
Building upon this data, the Institute for Information Industry (III) developed the smart Agri-management platform
(S.A.M.P.) as an integrated cloud service to support agri-business. Within S.A.M.P., a crop price forecasting service
is introduced, utilizing historical price data from the COA website as a training dataset. The service employs various
algorithms for time series analysis, including autoregressive integrated moving average (ARIMA), partial least
square (PLS), artificial neural network (ANN), and response surface methodology (RSM). Experimental results,
conducted on data from the First Fruit and Vegetable Wholesale Market in Taipei, reveal that PLS and ANN exhibit
lower error percentages compared to other algorithms, with PLS recommended for short-term and ANN for long-
term forecasting. The paper underscores the need for continuous improvement and expansion of forecasting models,
suggesting future research directions include incorporating additional features such as climate and market location,
and exploring evolutionary algorithms for feature selection as the dataset size increases.

"Developing crop price forecasting service using open data from Taiwan markets," 2015 Conference on
Technologies and Applications of Artificial Intelligence (TAAI).

The paper addresses the challenge of predicting agricultural prices in India, crucial for farmers' profitability,
especially given the country's significant poverty rate. By analyzing climatic conditions like temperature, humidity,

1447
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

pH, and rainfall, the method aims to anticipate the prices of fruits, vegetables, and pulses, aiding farmers in decision-
making regarding crop selection and potential earnings. Employing the Decision Tree Regression method, a
supervised machine learning algorithm, the approach utilizes data mining techniques to organize the dataset and
includes parameters such as weather conditions and market pricing. The results indicate promising accuracy levels,
with the model achieving validation accuracies of 89% using KNN, 90% with Random Forest, and 91.70% with the
Decision Tree Regressor on a large dataset. Comparative analysis demonstrates the superiority of the proposed
technique over existing methods, emphasizing the effectiveness of pre-trained models with Decision Tree Regressor
for agricultural price prediction. Overall, the study underscores the potential of machine learning algorithms,
particularly Decision Tree Regression, in enhancing agricultural price forecasting models, offering valuable insights
for farmers to optimize their crop selection and earnings.

Problem Statement :-
1. The agricultural sector is crucial in sustaining global economies by providing food and raw materials. However,
the agricultural supply chain faces various challenges that hinder its efficiency and transparency. The lack
oftraceability, information asymmetry, and inefficiencies in traditional supply chain processes lead to fraud,
wastage, and compromised product quality.
2. In the agricultural sector, producers face the challenge of optimizing profits through strategic pricing of their
crops. Currently, they receive information about competitors'prices and have data on the quantity of the produced
crop. However, determining the exact price point for maximum profit remains elusive.
3. In the context of Agricultural Supply Chain Management (ASCM), consumers face uncertainties related to the
pricing of organic and inorganic crops, which can significantly impact their decision-making processes. The lack of
accurate and timely information regarding stock prices for these crops poses challenges for both consumers, leading
to suboptimal choices, financial risks, and potential market inefficiencies.

Aim and Objective:-

Minimum Support Prices (MSP):
Set a floor price for the commodity, below which farmers are not allowed to sell. The government can purchase the
commodity at this price to support farmers during times of low market prices.

Enhanced traceability:
This can be done by using blockchain to create a tamper-proof record of every transaction in the supply chain, from
farm to fork. AI can also be used to analyze this data to identify trends and potential areas for improvement.

Increased transparency:
By using blockchain to create a transparent and secure record of every transaction in the supply chain, such a project
can help to increase transparency and build trust among stakeholders.

Cost reduction:
By improving efficiency and reducing waste in the supply chain, such a project can help to reduce costs for farmers
and other stakeholders.

Profitable Sales:
The predictions using AI will help both the producers and consumers gain profits via the sales.

Price Bands:
Define a price band within which the market price should ideally fluctuate. Intervene when prices fall below or rise
above this band to stabilize prices.

Proposed Methodology:-
Modern machine learning algorithms and the Ethereum blockchain are seamlessly integrated into the Agrarian.AI
system, which has a strong cloud basis. The core of the agricultural supply chain is essentially the Ethereum
blockchain, which provides transparent and safe record-keeping and transaction processing. A key function of smart
contracts is to provide a tamper-proof log of all operations from farm to table by automating interactions and
ensuring adherence to predefined terms. Enhancing data transparency and integrity through the use of blockchain
technology, Agrarian.AI builds trust amongst all parties involved in agricultural transactions.

1448
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

The Agrarian producer module.AI is carefully designed to enable farmers to easily manage the specifics of their
crops. Farmers may enter important data, like crop kind, amount, harvesting details, and expected price, using an
easy-to-use online interface, and the data will be automatically added to the Ethereum blockchain. Through the use
of a decentralised ledger to store data, this connection reduces the possibility of fraud and tampering in addition to
automating tasks like sales and distribution. Furthermore, farmers can benefit from predictive insights offered by
sophisticated machine learning algorithms like Support Vector Machines (SVM) and Random Forest, which help
with pricing and market placement through the examination of both historical and real-time data.

Agrarian.AI provides a user-friendly interface to help customers make well-informed purchasing decisions.
Customers can access detailed product information, including origin, quality, quantity available, and harvest dates,
stored on the Ethereum blockchain through the secure web portal. The data is contained in smart contracts enabled
by blockchain technology, which guarantees verifiability and immutability. This improves supply chain integrity and
product authenticity. Furthermore, using historical data and current market patterns, state-of- the-art machine
learning algorithms like Random Forest and SVM estimate the best timing and prices at which to make purchases,
giving customers financially solid suggestions.

Consumer interaction with the agriculture market is being revolutionised by the deliberate inclusion of predictive
analytics straight into the blockchain. This all-encompassing strategy not only yields better financial results but also
strengthens traceability and confidence across the supply chain. Agrarian.AI ushers in a new age of innovation in the
agriculture business by providing producers and consumers with unrivalled efficiency, security, and transparency via
the use of sophisticated machine learning algorithms and Ethereum blockchain technology. Agrarian.AI creates a
more successful and sustainable agricultural ecosystem by providing stakeholders with actionable data and utilising
blockchain's inherent benefits in record-keeping and transaction authenticity.

Figure 1:- Dataflow Diafram level 0.

Through the integration of state-of-the-art machine learning algorithms with Ethereum blockchain technology,
Agrarian.AI establishes a strong basis for transforming agricultural market transactions. The platform's skillful use
of smart contracts guarantees the safe and transparent documentation of transactions, automating correspondence,
and ensuring compliance with pre-established conditions. Predictive analytics is also made possible by the
incorporation of machine learning algorithms like Support Vector Machines (SVM) and Random Forest, which help
producers position themselves in the market and choose the best prices. In addition to increasing economic

1449
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

efficiency, this clever technology combination promotes confidence and openness throughout the agricultural supply
chain, paving the way for the sector to have a more prosperous and sustainable future.

System Design:-
The Agrarian system design is designed to smoothly incorporate Ethereum blockchain technology and cutting-edge
machine learning algorithms into a solid cloud-based architecture. The Ethereum blockchain is fundamental to the
platform's secure and transparent record-keeping and transaction processing. Smart contracts offer a tamper-proof
ledger of all transactions from farm to table, automating interactions and guaranteeing adherence to agreed terms. In
order to predict the best pricing strategies, the system also uses dual machine learning models, Support Vector
Machines (SVM), and Random Forest, which each independently analyses historical and current agricultural data.
Following a comparison of these predictions, the top results are dynamically chosen and made available to users via
an intuitive web interface. In order to guarantee data security and integrity, the design also incorporates role-based
access controls. A backend API makes it easier to handle data effectively and integrate it with other systems,
completing a scalable and adaptable architecture that is ready to be expanded into a variety of agricultural markets.

Producer Module:
The producer module of the Agrarian.AI system has been carefully crafted to enable farmers to input and manage
the details of their crops. These details are then seamlessly integrated into the Ethereum blockchain for increased
security and transparency. Through an intuitive web interface, producers can enter vital data like crop type, quantity,
harvesting data, and anticipated pricing. These submissions result in their encoding within Ethereum blockchain
smart contracts. In addition to ensuring the automation of processes like sales and distribution, this integration safely
stores data in a decentralized ledger to prevent fraud and tampering. Additionally, the platform uses sophisticated
machine learning algorithms, namely Support Vector Machines (SVM) and Random Forest, to enhance pricing
strategies and producers' market positioning. These algorithms dynamically generate predictive insights about
pricing trends and market demand by analysing real-time and historical data. By incorporating these forecasts into
the blockchain, all parties involved in the agricultural supply chain can make better decisions and benefit from
increased transparency as each transaction is guided by insights derived from data.

Customer Module:
The customer module of the Agrarian.AI system is purposefully designed to give users clear and data-driven
purchasing options. Customers can obtain detailed information about a range of agricultural products, securely
stored on the Ethereum blockchain, including origin, quality, quantity available, and harvest dates, via an easy-to-
use and secure web interface. Encapsulated within blockchain-enabled smart contracts, this data guarantees every
piece of information is verifiable and immutable, boosting supply chain integrity and product authenticity
trustworthiness. Furthermore, the platform uses two cutting-edge machine learning algorithms— Random Forest and
Support Vector Machines (SVM)—to help users make economically sound decisions. These algorithms forecast the
best times and prices to make purchases by analysing past data along with current market trends. The platform
guarantees that consumers receive a transparent, real-time tool for making decisions that helps them optimize their
spending and maximize value from their purchases by directly integrating these predictive insights into the
blockchain. This will revolutionize the way consumers engage with the agricultural market.

Blockchain Module:
Finally, Agrarian.AI transforms the agricultural supply chain by utilizing the strength of the Ethereum blockchain in
conjunction with cutting-edge machine learning algorithms like Random Forest and Support Vector Machines
(SVM). The platform offers unmatched efficiency, security, and transparency for producers and consumers by
integrating these technologies. In addition to smart contracts for automated business transactions and blockchain's
unchangeable record- keeping for transaction authenticity, producers gain useful insights from predictive analytics
for optimal pricing strategies. On the other hand, customers are equipped with comprehensive product details and
intelligent buying suggestions, enabling them to make well-informed choices. This all-encompassing strategy not
only improves economic results and increases trust and traceability throughout the supply chain, but it also opens the
door to a more lucrative and sustainable agricultural ecosystem.

1450
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

Use Case Diagram

Producer Module:

Figure 2:- UCD for Producer module.

Figure 3:- UCD for Customer module.

Result:-
The Agrarian.AI project achieved key outcomes through its three main modules, detailing both the methodologies
and their impacts:

Producer Pricing Module:

Implementation:
We analyzed historical market data using Random Forest and SVM algorithms to generate optimal price suggestions
for producers. By comparing the outputs of both algorithms, we ensured that the best-performing price was
recommended.

Impact:
Producers reported an increase in sales due to more competitive pricing. The ability to receive data-driven pricing
suggestions empowered producers to make informed decisions, enhancing their market positioning.

1451
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

Consumer Price Selection:

Implementation:
We developed a feature that aggregates and analyzes local market data to present the top five best prices for
agricultural products in a specific region, using both Random Forest and SVM to ensure relevance and accuracy.

Impact:
Consumers found the curated list of prices more relevant and appealing, leading to a better purchasing experience.
This feature facilitated informed decision-making among consumers, ultimately enhancing their satisfaction with the
platform.

Transaction Transparency with Blockchain:

Implementation:
We integrated a blockchain-based payment gateway using MetaMask, which recorded all transactions on an
immutable ledger, providing transparency and security.

Impact:
This approach significantly reduced transaction discrepancies, fostering trust among users. The transparent nature of
the recorded transactions encouraged greater user engagement on the platform, contributing to a more reliable
transaction process.

Overall, Agrarian.AI not only optimized pricing strategies and enhanced consumer choices but also ensured
transparency in transactions, positively transforming the agricultural marketplace.

Future Enhancements:-
1. Integration of IoT Devices: The inclusion of Internet of Things (IoT) devices into the supply chain can offer real-
time monitoring of environmental conditions like temperature, humidity, and soil moisture. This data can enhance
traceability and quality assurance by continuously tracking product conditions throughout the supply chain.
2. Expansion of Predictive Analytics: Continuously refining and broadening predictive analytics capabilities can
provide more accurate forecasts of pricing trends, demand fluctuations, and supply chain disruptions. This enables
proactive decision-making and risk management strategies to optimize supply chain operations.
3. Enhanced Interoperability: Improving interoperability between various blockchain networks and supply chain
platforms can facilitate seamless data exchange and collaboration among stakeholders. Standardizing protocols and
interfaces streamline information flow, enhancing transparency across the supply chain ecosystem.
4. Integration with Sustainable Practices: Integrating sustainability metrics and certifications into the traceability
model offers consumers insights into the environmental and social impact of agricultural products. This aligns with
increasing consumer demand for ethically sourced and eco-friendly products.
5. Blockchain Scalability Solutions: Deploying scalable blockchain solutions like sharding or sidechains addresses
scalability challenges and accommodates the growing volume of transactions and data. This ensures the continued
reliability and performance of the decentralized traceability model.
6. Enhanced User Experience: Improving user interfaces and mobile applications enhances the accessibility and
usability of the traceability platform for producers and consumers. Providing personalized recommendations and
notifications boosts engagement and trust among users
7. Integration of Geospatial Data: Including geospatial data and mapping technologies offers additional insights into
the geographical origin and journey of agricultural products. This enhances traceability and enables targeted
interventions based on geographic-specific challenges.
8. Collaboration with Regulatory Bodies: Partnering with regulatory bodies and industry associations to establish
industry-wide standards and regulations for blockchain-based traceability systems fosters trust and adoption.

Conclusion:-
The transition to a decentralized traceability model in agricultural supply chain management signifies a pivotal
advancement towards augmenting transparency, quality assurance, and traceability. This strategic pivot froma
centralized systemto a decentralized approach, powered by blockchain technology, addresses the shortcomings of
conventional supply chains and fosters enhanced communication and collaboration among stakeholders. By
harnessing blockchain technology and integrating machine learning algorithms like Support Vector Machines
(SVM) and Random Forest, the Agrarian.AI platform delivers unparalleled transparency.

1452
ISSN: 2320-5407 Int. J. Adv. Res. 12(09), 1444-1453

Smart contract’s introduction ensures automated and tamper-proof transaction processing, while predictive analytics
arm stakeholders with invaluable insights into pricing trends and market demand, optimizing profitability for
producers and enabling consumers to make informed purchasing decisions. Furthermore, the integration of
blockchain technology fortifies data integrity and authenticity, instilling trust and confidence throughout the supply
chain.

Moreover, this strategic adoption of a decentralized approach not only improves economic outcomes but also
increases trust and traceability across the supply chain. By combining cutting-edge technologies with innovative
methodologies, the Agrarian.AI platform propels the agricultural industry towards greater sustainability and
efficiency.

References:-
[1] Fiore, M., & Mongiello, M. "Blockchain technology to support agri-food supply chains: A comprehensive
review," in IEEE Access, vol. 11, pp. 75311-75324, 2023. doi: 10.1109/ACCESS.2023.3296849.
[2] Hegde, G., Hulipalled, V. R., and Simha, J. B. "A study on agriculture commodities price prediction and
forecasting," in 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics
(ICSTCEE), Bengaluru, India, 2020, pp. 316-321. doi: 10.1109/ICSTCEE49637.2020.9277401.
[3] Lin, W., et al. "Blockchain technology in current agricultural systems: From techniques to applications," in IEEE
Access, vol. 8, pp. 143920-143937, 2020. doi: 10.1109/ACCESS.2020.3014522.
[4] Misra, S., & Sugandh, U. "Blockchain in agriculture to ensure trust, effectiveness, and traceability from farm
fields to groceries," in *Future Internet*, vol. 15, no. 12, p. 404, 2023. doi: 10.3390/fi15120404.
[5] Misra, S., & Sugandh, U. "Exploring the role of Blockchain technology in modern high-value food supply
chains: Global trends and future research directions," in Agricultural and Food Economics, 2023. Retrieved from
https://agrifoodecon.springeropen.com/articles/10.1186/s40100-023-00274-1.
[6] Patil, A., Kumar, R., Sharma, M., and Bhardwaj, A. "Leveraging blockchain and IoT for smart agriculture," in
IEEE Internet of Things Journal, vol. 10, no. 4, pp. 3140-3151, 2023. doi: 10.1109/JIOT.2023.0023412.
[7] Raza, Z., Haq, I. U., and Muneeb, M. "Agri-4-All: A framework for blockchain-based agricultural food supply
chains in the era of Fourth Industrial Revolution," in IEEE Access, vol. 11, pp. 29851-29867, 2023. doi:
10.1109/ACCESS.2023.3259962.
[8] Rao, S., Kumar, A., Sharma, S., and Dubey, P. "Blockchain technology for agriculture: Applications and
rationale," in Frontiers in Blockchain, 2023. Retrieved from
https://www.frontiersin.org/articles/10.3389/fbloc.2023.00001/full.
[9] Sajithabanu, S., Ponmalar, A., Soundari, A. G., Reshma, N., Sunraja, K., and Sindhumathi, R. "Enhanced crop
price prediction & forecasting system," in 2022 International Conference on Computer, Power and Communications
(ICCPC), Chennai, India, 2022, pp. 580-585. doi: 10.1109/ICCPC55978.2022.10072183.
[10] Shi, J., Wang, Y., Liu, W., Yang, L., and Ma, X. "Blockchain-based traceability for agricultural products: A
systematic literature review," in MDPI Agriculture, vol. 13, no. 1, pp. 1-20, 2023. doi:
10.3390/agriculture13010001.
[11] Shivendra, K., Chiranjeevi, K., Tripathi, M. K., and Maktedar, D. D. "Blockchain technology in agriculture
product supply chain," in 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS),
Coimbatore, India, 2021, pp. 1325-1329. doi: 10.1109/ICAIS50930.2021.9395886.
[12] Sugandh, U., Nigam, S., and Khari, M. "Blockchain technology in agriculture for Indian farmers: A systematic
literature review, challenges, and solutions," in IEEE Systems, Man, and Cybernetics Magazine, vol. 8, no. 4, pp.
36-43, Oct. 2022. doi: 10.1109/MSMC.2022.3197914.
[13] Thapaswini, G., and Gunasekaran, M. "A methodology for crop price prediction using machine learning," in
2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC), Tumkur,
Karnataka, India, 2022, pp. 1-7. doi: 10.1109/ICMNWC56175.2022.10031852.
[14] Peng, Y.-H., Hsu, C.-S., and Huang, P.-C. "Developing crop price forecasting service using open data from
Taiwan markets," in 2015 Conference on Technologies and Applications of Artificial Intelligence (TAAI), Tainan,
Taiwan, 2015, pp. 172-175. doi: 10.1109/TAAI.2015.7407108.
[15] Sharma, C., Misra, R., Bhatia, M., and Manani, P. "Price prediction model of fruits, vegetables, and pulses
according to weather," in 2023 13th International Conference on Cloud Computing, Data Science & Engineering
(Confluence), 2023, pp. 347-351. doi: 10.1109/Confluence56041.2023.10048880.

1453