Scribd Logo
Upload

Welcome to Scribd!

  • 7 views

    GISTI LAB 6 - PAO I 2024 - Machine Learning y Deep Learning

    Uploaded by

    erickf

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    GISTI LAB 6 - PAO I 2024 - Machine Learning y Deep Learning

    Uploaded by

    erickf
    7 views2 pages

    Original Title

    GISTI LAB 6 - PAO I 2024_ Machine Learning y Deep Learning

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    7 views2 pages

    GISTI LAB 6 - PAO I 2024 - Machine Learning y Deep Learning

    Uploaded by

    erickf

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    GISTI LAB 6 - PAO I 2024: Machine Learning y Deep Learning

    Members:
    ● Erick Flores
    ● Richard Núñez

    CASE STUDY: MACHINE LEARNING

    Banco Guayaquil: Enhancing Customer Loan Approvals with Machine Learning

    Banco Guayaquil implemented a machine learning (ML) solution to improve the accuracy
    and efficiency of its customer loan approval process. Historical loan application data,
    including customer demographics, financial history, and repayment records, were collected
    and preprocessed. The data science team employed supervised learning techniques, using
    algorithms such as logistic regression, decision trees, and random forests. The model was
    trained on labeled data where the outcome (loan repaid or defaulted) was known. The model's
    performance was validated using cross-validation techniques and evaluated with metrics such
    as accuracy, precision, recall, and the F1 score. The final model was integrated into Banco
    Guayaquil's loan processing system, enabling loan officers to make more informed approval
    decisions.

    CASE STUDY: DEEP LEARNING

    Banco Guayaquil: Fraud Detection with Deep Learning

    Banco Guayaquil implemented a deep learning solution to detect fraudulent transactions in


    real-time. Transaction data, including timestamps, transaction amounts, merchant details, and
    geographic locations, were collected and augmented to create a balanced dataset. A deep
    learning model using Long Short-Term Memory (LSTM) networks was developed to analyze
    sequential transaction data. The model was trained to identify normal versus fraudulent
    transaction patterns based on historical data. After extensive hyperparameter tuning and
    optimization, the model was deployed in Banco Guayaquil’s transaction monitoring system.
    Real-time transaction data was fed into the model, which flagged potentially fraudulent
    activities for further investigation.

    CONCLUSIONS

    Banco Guayaquil's implementation of machine learning and deep learning solutions has
    significantly enhanced its operational capabilities. The machine learning model for loan
    approval improved decision accuracy and reduced default rates, while the deep learning
    model for fraud detection provided robust real-time protection against fraudulent activities.
    These case studies illustrate the transformative impact of advanced analytics in the banking
    sector, demonstrating the value of leveraging machine learning and deep learning to drive
    efficiency, accuracy, and customer trust.

    References
    Brownlee, J. (2019). Pima Indians Diabetes Dataset. Retrieved from Machine Learning
    Mastery.

    LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to
    document recognition. Proceedings of the IEEE, 86(11), 2278-2324.

    You might also like