You will get a Machine Learning powered App to detect Fraud transactions
Project details
I have built a powerful fraud detection system using machine learning. This is a typical example of a full stack Python data science project! Starting from data gathering, processing, feature engineering, handling class imbalance, prediction, cross-validation with an impressive 94% accuracy, deployment into Streamlit, dockerization , github and hosting a scalable streamlit UI/App.
This UI app can be used by banks to detect fraudulent transaction requests from customers and mitigate risk. It can be plugged into the software of bank executives who will enter the requested transaction amount, last and new balances of sender and receiver, whenever a new transaction request comes up. The app uses the backend classification model trained on past transactions data which identifies whether the transaction is "Fraudulent" or "Legit". It can be monitored at regular frequency and versions can be maintained via Github and CI/CD pipelines.
What you get?
• Machine Learning prediction model tagging incoming transactions as Fraud/Legit
• Top factors that help differentiate a Fraud and Legit transaction
• Front end UI to enter transaction details and get output
This UI app can be used by banks to detect fraudulent transaction requests from customers and mitigate risk. It can be plugged into the software of bank executives who will enter the requested transaction amount, last and new balances of sender and receiver, whenever a new transaction request comes up. The app uses the backend classification model trained on past transactions data which identifies whether the transaction is "Fraudulent" or "Legit". It can be monitored at regular frequency and versions can be maintained via Github and CI/CD pipelines.
What you get?
• Machine Learning prediction model tagging incoming transactions as Fraud/Legit
• Top factors that help differentiate a Fraud and Legit transaction
• Front end UI to enter transaction details and get output
Machine Learning Tools
ChatGPT, NumPy, pandas, Python, Python Scikit-Learn, PyTorch, scikit-learn, SQL, TensorFlow, XGBoostWhat's included
| Service Tiers |
Starter
$20
|
Standard
$40
|
Advanced
$50
|
|---|---|---|---|
| Delivery Time | 7 days | 7 days | 10 days |
Number of Revisions | 1 | 1 | 1 |
Model Validation/Testing | |||
Model Documentation | |||
Data Source Connectivity | - | ||
Source Code | - | - |
About Prerana
Machine Learning Engineer - Predictive Analytics for BFSI
Gurgaon, India - 11:16 pm local time
With hands-on experience in developing, training, and deploying machine learning models, I bring both technical expertise and a deep understanding of how to translate data into meaningful insights that drive business value.
Over the past few years, I’ve worked extensively on projects involving predictive modeling, statistical analysis, and data visualization. My skill set includes Python (pandas, scikit-learn, NumPy, matplotlib, seaborn, Plotly), as well as tools like Power BI for interactive reporting. I have successfully built and optimized models for classification, regression, and clustering, while presenting results through compelling visualizations that help non-technical stakeholders make informed decisions.
I can deliver high-quality visualizations, charts. I focus on accuracy, interpretability, and design clarity—ensuring that each visualization tells a clear story supported by robust data science methods.
I’m passionate about leveraging GenAI and machine learning to solve real-world problems, and I’m confident that my technical skills and attention to analytical storytelling align perfectly with business needs.
Sample projects are listed below:
- Leads generation
- Churn Modelling
- Fraud detection
- Sentiment analysis
- Clustering and segmentation
- Classification prediction
- Text to SQL using GenAI
- Hyperpersonalization using GenAI, LLM and Machine Learning
- Data Analysis and visualization using power BI or Tableau
- Corrective RAG using Visual studio code
- Customer Lifetime Value calculation
- Excel data analysis
Steps for completing your project
After purchasing the project, send requirements so Prerana can start the project.
Delivery time starts when Prerana receives requirements from you.
Prerana works on your project following the steps below.
Revisions may occur after the delivery date.
Overview of business requirement
Data provision