Crop suggestion based on agro factors and market price

A
Seminar Report
Submitted to
Jawaharlal Nehru Technological University, Hyderabad in
Partial Fulfilment of the requirements for the Award of the Degree
of

Bachelor of Technology
Computer Science in Data Science
By
MERUGU VENU 21E11A6725

Under the Guidance of

Dr .SRI LAKSHMI E
Assistant Professor, Department of Electrical and Electronics Engineering

Department Computer Science and Engineering

BHARAT INSTITUTE OF ENGINEERING AND TECHNOLOGY

(Affiliated to JNTU Hyderabad, Approved by AICTE, Accredited by NAAC)
Ibrahimpatnam – 501 510, Hyderabad, Telangana
2021-2025 Batch
 BHARAT INSTITUTE OF ENGINEERING AND TECHNOLOGY
(Affiliated to JNTU Hyderabad, Approved by AICTE, Accredited by NAAC)
Ibrahimpatnam – 501 510, Hyderabad, Telangana

CERTIFICATE
This is to certify that the seminar project work entitled “Crop suggestion based on
agro factors and market price” is a beneficial project work carried out by

MERUGU VENU 21E11A6725

in the department of Computer Science In Data Science at Bharat Institute of Engineering

and Technology, Hyderabad is submitted to Jawaharlal Nehru Technological University,
Hyderabad in partial fulfilment of the requirements for the award of the degree of
Bachelor of Technology degree in Computer Science In Data Science during 2024-25.

Guide: Head of the Department:

Dr . Sri Lakshmi E Dr . Sri Lakshmi E

Associate Professor Associate Professor
Dept. of EEE Dept. of EEE,
BIET, Hyderabad. BIET, Hyderabad.

Principal
BIET, Hyderabad.

Viva-Voce held on: ______________

List of examiners Signature with date
1. Internal Examiner
2. External Examiner
 BHARAT INSTITUTE OF ENGINEERING AND
TECHNOLOGY
(Affiliated to JNTU Hyderabad, Approved by AICTE, Accredited by NAAC)
Ibrahimpatnam – 501 510, Hyderabad, Telangana

DECLARATION

I, MERUGU VENU (21E11A6725), hereby declare that this Seminar Report titled
“Crop suggestion based on agro factors and market price” is a genuine work
carried out by me in the B.Tech (Computer Science and Engineering – Data
Science) degree course of Jawaharlal Nehru Technological University,
Hyderabad and has not been submitted to any other course or university for
the award of the degree by us.

MERUGU VENU 21E11A6725

Submitted By :
Name: MERUGU VENU
21E11A6725
SEMESTER 7TH
 ACKNOWLEDGEMENT

Over a span of one year, BIET has helped us transform ourselves from were
amateurs in the field of Computer Science into skilled engineers capable of handling
any given situation in real time. We are highly indebted to the institute for everything
that it has given us.

I would like to express my gratitude towards the principal of our institute, and the Head of
the CSE Department, for their kind cooperation and encouragement which helped us
complete the project in the stipulated time.

Although we have spent a lot of time and put in a lot of effort into this Seminar project,
it would not have been possible without the motivating support and help of our project
guide I thank him for his guidance, constant supervision and for providing necessary
information to complete this project.. Our thanks and appreciations also go to all the
faculty members, staff members of BIET, who have helped me put this project
successfull .
 ABSTRACT

Agriculture plays a major role in the Indian economy, but choosing

the right crop can be challenging due to factors like soil composition,
climate change, and market changes. The Crop Advisory System
(CSS) addresses these issues by integrating real-time data with
predictive analysis, giving farmers better planning tools. In addition
to traditional considerations like land type and security, CSS also
factors in economic elements such as market demand and cost
fluctuations. Using AI-powered machine learning and deep neural
networks, it analyzes large datasets to identify patterns and
correlations, offering insights on the best planting times for specific
regions and crops. This guide helps farmQ2ers reduce risks, avoid
losses, and enhance productivity. As markets evolve and new data
emerges, the system updates its recommendations, empowering
farmers to make decisions that boost productivity and promote
sustainable growth.
 List of contents

S.NO Title
1 Introduction
1.1 Objective
1.2 1 1.2 Preview
1.3 Motivation

1.4 Scope Of Work

2 Literature Survey
3 Software Requirements Analysis
Software and Hardware Requirements
• Hardware Requirements
• Software Requirements

4 Proposed System
4.1 System Architecture
4.2 UML Diagrams
• Use case Diagram
• Class Diagram
• Sequence Diagram

5: Implementation

6: Results

7.Conclusion and Future Scope

1.INTRODUCTION:

1.1.Objective :

The objective of the Crop Suggestion System (CSS) is to assist farmers in

selecting optimal crops for their farms by providing personalized
recommendations based on factors like soil type, pH level, temperature, humidity,
nutrient availability, and market prices. By leveraging advanced data analytics
and machine learning, the CSS aims to enhance agricultural productivity,
financial returns, and environmental sustainability.

1.2.Preview :

The CSS is an innovative tool designed to provide farmers with personalized crop
recommendations through advanced data analysis and machine learning
algorithms. It offers a user-friendly interface accessible on both laptops and
mobile devices, allowing farmers to receive insights tailored to their specific farm
conditions.
The system proposes a flexible three-crop recommendation model, which
suggests the top three crops based on environmental factors using a neural
network model. Additionally, the CSS encourages collaboration among farmers
by integrating a feedback mechanism and promoting community engagement,
making it a comprehensive solution for modern agriculture.
1.3.Motivation :

The agriculture industry faces constant challenges, including fluctuating

commodity prices and unpredictable weather conditions, which can significantly
impact crop yields and farmers' income. The need for more resilient, data-driven
solutions inspired the development of the CSS, which seeks to mitigate these
challenges by helping farmers make better-informed decisions about crop
selection.

By harnessing historical data and predictive analytics, the CSS not only
boosts yields but also helps farmers stay ahead of market trends and
environmental changes, supporting long-term agricultural sustainability and
financial stability.

1.4.Scope of Work

1. Data Analysis: The CSS analyzes a range of environmental factors, including

soil characteristics, temperature, humidity, and nutrient levels, to make
informed crop recommendations.

2. Machine Learning Algorithms: It utilizes predictive analytics and historical

data through machine learning models to determine the optimal crop choices
for various farm conditions.

3. Three-Crop Recommendation Model: The system employs a neural network

with 20 neurons in the output layer, providing the top three crop options based
on real-time farm data.

4. User Interface: The CSS is accessible via laptops and mobile devices,
designed for ease of use by farmers with different levels of technical expertise.
 5. Feedback Mechanism: Farmers can provide feedback on the system’s
performance and recommendations, which will be used to improve the system
over time.

6. Community Collaboration: The CSS promotes communication among

farmers, allowing them to share insights, experiences, and strategies, further
enhancing the system’s effectivene

2.LITERATURE SURVEY :

Smart farming using Machine Learning and Deep Learning techniques

This paper discusses a sophisticated combination of ResNet152V2 for image-

based analysis, particularly useful in tasks like plant disease detection, and
traditional machine learning algorithms like SVM, KNN, decision tree, and
neural networks for analyzing large datasets related to soil, climate, and crop
conditions.

The integration of these techniques enables smart farming systems to make

real-time, datadriven decisions, enhancing crop management and productivity.
The research highlights the potential for deep learning models to handle high-
dimensional data, especially in precision agriculture.

Crops yield prediction based on machine learning models

This study provides a systematic framework for crop yield prediction by
comparing different machine learning models such as Decision Tree, KNN, and
Multivariate Logistic Regression. It emphasizes the importance of model
selection based on the characteristics of the dataset, exploring how different crops
and regions affect the model's performance.

The paper also discusses the impact of feature engineering and parameter
tuning in optimizing the models, ensuring better prediction accuracy for yield
forecasting.
Machine learning for large-scale crop yield forecasting
The paper combines IoT devices for real-time data collection, creating a robust
ecosystem for managing large-scale farms. By using advanced machine learning
techniques like SVM, KNN, Naive Bayes, Random Forests, and deep learning
models such as CNN and RNN, the research improves crop yield forecasting over
extended regions.

The large-scale focus allows the study to explore the scalability of machine
learning models, addressing the computational challenges faced when working with
vast agricultural datasets.

Machine Learning Applications for Precision Agriculture

This paper integrates IoT sensors with a range of machine learning models like
KNN, ANN, CNN, SVM, Random Forest, and Gradient Boosting to deliver
precision agriculture solutions.

By collecting and analyzing data on soil moisture, temperature, and

nutrient levels, the models help farmers optimize resource allocation. The study
also examines the role of deep learning models such as CNNs in detecting
diseases and pests from image data, offering a comprehensive toolset for
precision farming.

Market Price, Crop, and Crop Yield Prediction Using Machine Learning
By applying Random Forest and the Back Propagation Algorithm, this paper
focuses on predicting both market prices and crop yields. The study highlights the
importance of incorporating market dynamics, such as supply-demand
fluctuations, into crop yield predictions.
The integration of these economic factors with environmental data improves the
robustness of the models, offering a comprehensive solution for agricultural
forecasting.

3.SYSTEM REQUIREMENTS
SOFTWARE:
• Python 3.x: Python is the primary programming language for
developing the application, so it must be version 3.x to leverage the
latest features and libraries.
• Jupyter Notebook: This tool is used for developing and testing code
interactively, making it easier to explore and visualize data.
• Django: A high-level Python web framework used for building and
deploying the web application, which integrates with the machine
learning model.
Libraries: Pandas, NumPy, Scikit-Learn, and Joblib or Pickle.
HARDWARE:
 • Operating System: The system should be compatible with any of the
major operating systems: Windows, macOS, or Linux.
• Memory: The machine should have at least 8GB of RAM to ensure
smooth operation and efficient processing of data.
• Processor: A multi-core processor is required to handle concurrent
tasks effectively, such as data processing and model training.

3.PROPOSED SYSTEM

ARCHITECTURE:

The following steps outline the key phases of the project:

1. The dataset used in this project was collected from Kaggle, UCI
Machine Learning Repository, internal databases.
2. Dataset Collection and Preprocessing-involves dataset collection
and preprocessing.
3. The dataset was split into training and testing sets with a ratio of
[e.g., 80:20]. Cross-validation was employed using like k-fold
 cross-validation to optimize model performance and ensure
generalization.
4. Models used include Decision Tree, Random Forest, SVM, Naive
Bayes, and Logistic Regression for classification of the correct
crop.

5. The model's performance was evaluated using accuracy,

precision, recall, and F1score, with validation showing an
accuracy percentage and metric value.
6. The trained model was serialized and integrated into the Django
application with an API endpoint for real-time predictions.

5. SYSTEM DESIGN
CLASS DIAGRAM :

The Crop Suggestion System (CSS) assists farmers in selecting the most
suitable and profitable crops by analyzing agro-environmental factors and
market prices. The system’s core components include the Farmer,
AgroFactors, CropPredictionModel, Crop, and
CropSuggestionBasedOnPrice classes.The Farmer inputs key agro factors
like rainfall, temperature, humidity, and soil nutrients (nitrogen,
phosphorus, potassium), managed by the AgroFactors class. The
CropPredictionModel processes these inputs using machine learning
algorithms (e.g., Random Forest) to suggest a list of suitable crops, each
represented by the Crop class, which contains crop names and suitability
scores.

SEQUENCE DIAGRAM :

The sequence diagram illustrates the workflow of the Crop Suggestion

System. The farmer enters agro factors (e.g., rainfall, temperature) via the
user interface (UI). These inputs are sent to the Crop Prediction Model,
which processes the data and predicts 4-5 suitable crops based on
environmental conditions. The predicted crops are then forwarded to the
Crop Suggestion Based on Price component to retrieve their current
market prices. Once the price data is returned, the UI displays the
suggested crops along with their prices to the farmer, helping them make
informed, data-driven decisions for crop selection.
5.3. ACTIVITY DIAGRAM

The flowchart illustrates the key steps in the Crop Suggestion System
process. It starts with the Input of Agro Factors, where the farmer enters
relevant environmental data (e.g., temperature, rainfall). Next, the system
Preprocesses the Agro Factors to ensure the data is suitable for analysis.
The Crops Prediction phase then uses machine learning models to suggest
a list of suitable crops. These predicted crops undergo the Crop

.
Suggestion Based on Price stage, where their market prices are retrieved.
Finally, the system Displays Suggested Crops to the farmer, helping them
make informed decisions about what to plant.
USECASE DIAGRAM:

The diagram represents a system designed to suggest suitable crops for

farmers based on agro environmental factors and market prices using a
machine learning model. The process begins with the Farmer inputting
agro factors (such as soil type, climate conditions, and other
environmental data) into the User Interface (UI).

Next, the system performs Data Preprocessing and Feature Selection to

clean and prepare the data for prediction. The ML Model then uses these
agro factors to predict suitable crops in the Crops Prediction phase. Once
the possible crops are predicted, the system moves on to Crop Suggestion
Based on Price, where it evaluates the market prices and suggests the most
profitable crop for the farmer to cultivate.

6. IMPLEMENTATION
Here's a detailed implementation of the crop suggestion system based on agro-
factors and market price:

Step 1: Data Collection:

 • Collect data on agro-factors such as climate, soil type, and water availability from
various sources such as government databases, weather APIs, and soil surveys.
• Collect data on market prices of various crops from sources such as
government databases, market research reports, and online marketplaces.
• Create a database of various crops, including their characteristics, growth
requirements, and market demand.

Step 2: Data Preprocessing

• Clean and preprocess the collected data to prepare it for machine learning
modeling.
• Handle missing values and outliers in the data.
• Normalize the data to ensure that all features are on the same scale.

Step 3: Feature Engineering

• Extract relevant features from the preprocessed data to use in machine learning
modeling.
• Use techniques such as correlation analysis and recursive feature elimination to
select the most important features.

Step 4: Model Selection:

• Select a suitable machine learning algorithm (e.g., decision trees, random

forests, neural networks) to develop the suggestion engine.
• Use techniques such as cross-validation and grid search to evaluate the
performance of different algorithms and hyperparameters.

Step 5: Model Training

• Train the selected machine learning model using the preprocessed data.
• Use techniques such as early stopping and learning rate scheduling to prevent
overfitting and improve model performance.

Step 6: Model Evaluation

• Evaluate the performance of the trained model using metrics such as accuracy,
precision, and recall.
• Use techniques such as confusion matrices and ROC curves to visualize model
performance and identify areas for improvement.
Step 7: Deployment

• Deploy the trained model in a production-ready environment.

• Use techniques such as containerization and orchestration to ensure scalability
and reliability.

7. RESULTS & OUTPUT SCREENS

CONCLUSIONS :
The Crop Suggestion System (CSS) developed in this project presents a
modern solution to enhancing agricultural productivity through the
application of machine learning and data analytics. By leveraging
powerful algorithms such as Random Forest, SVM, and XGBoost, the
system delivers accurate recommendations for crop selection based on
various factors like soil nutrients, weather conditions, and market prices.
The integration of a multi-crop recommendation model further enhances
the system’s utility, offering farmers not only a single crop suggestion but
also a top-three list of potential crops for maximum yield and profitability.
Additionally, neural networks contribute to the precision of these
recommendations, allowing the system to support more informed
decision-making and improve farming outcomes.

The Random Forest model showed near-perfect classification accuracy

when tested on a balanced dataset, ensuring that farmers can rely on the
system for high-certainty predictions. The system is designed to be
adaptable and scalable, making it capable of incorporating future
technological advancements while maintaining sustainability. The overall
framework of the CSS aligns well with long-term economic goals, giving
farmers the tools to make smarter decisions and optimize their agricultural
practices.
FUTURE SCOPE:
1. Integration of Advanced Data Sources: In the future,
the Crop Suggestion System can be enhanced by
integrating additional data sources, such as satellite
imagery or realtime sensor data, which could improve the
accuracy of crop recommendations. These sources would
allow the system to provide more granular insights into
soil conditions and weather patterns, helping farmers
make even more precise decisions.
2. Incorporation of Advanced Weather Models: To
further improve crop recommendations, incorporating
sophisticated weather forecasting models could enable the
system to predict and respond to extreme weather events.
This would be especially useful for mitigating risks and
ensuring the sustainability of crops in the face of
unpredictable climate changes.
 3. Automated Decision Support and Precision
Agriculture: The CSS could evolve into a
comprehensive decision-support tool that includes
features such as precision agriculture techniques and
automated resource management optimizations. This
would empower farmers with real-time insights on
irrigation, pesticide usage, and crop rotation, thereby
increasing efficiency and reducing waste.
4. Expansion of Crop Recommendations for
Different Regions: The system can be adapted to cater
to different agricultural regions with unique soil and
climate conditions. Customizing the model to
accommodate diverse farming environments will make
CSS more versatile and widely applicable.
5. Continuous Learning and Technological
Integration: As emerging technologies like IoT and AI
evolve, the system could integrate with these innovations
to offer real-time feedback and decision-making
capabilities. Continuous learning algorithms can be
incorporated to update recommendations based on
changing market prices, new crops, or unforeseen
environmental shifts, making the CSS a dynamic tool for
modern agriculture.
By incorporating these advancements, the Crop Suggestion System has
the potential to revolutionize farming practices globally, contributing to
improved food security and sustainable agricultural development.

9. REFERENCES
[1] M. Kalimuthu, P. Vaishnavi, and M. Kishore. "Crop Prediction
using Machine Learning." 2020 3rd International Conference on
Smart Systems and Inventive Technology (ICSSIT 2020), IEEE-2020.
[2] D. Elavarasan and P. M. Durairaj Vincent. "Crop Yield Prediction
Using Deep Reinforcement Learning Model for Sustainable Agrarian
Applications. 3rd International Conference on Communication and
Electronics Systems (ICCES)IEEE-2020. [3] Madhuri Shripathi Rao,
Arushi Singh,and N.V. Subba Reddy. "Crop prediction using machine
learning Approaches".2022 3rd International Conference on Artificial
Intelligence, Computational Electronics and Communication Systems
(AICECS), IEEE2022.
[4] Janmejay Pant, R.P. Pant, Manoj Kumar Singh, Devesh Pratap
Singh, and Himanshu Pant. "Analysis of agricultural crop yield
prediction using statistical techniques of machine learning."
International Conference on Smart Technologies and
Management for Computing, Communication, Controls, Energy
and Materials (ICSTM)-2015.
[5] Ganesh Sastry Kakaraparthi*1, B.V.A.N.S.S.Prabhakar
Rao*2"CROP PRICE PREDICTION USING MACHINE
LEARNING" 2022 International Research Journal of
Modernization in Engineering Technology and Science .