Still Struggling with Tech Hiring? Discover Olibr's Solution Now!
Login / RegisterDeveloperClient
Login/Register

KANCHAN MESHRAM

ML Project Engineer(Data Scientist)

  • Nagpur, MH
  • 3 years

Available From: Available

    Candidate's About

    With 3.6 years of experience building and maintaining ML/DL projects with the highest accuracy, I am a solution-oriented problem solver proficient in using Python, Pandas, and Numpy. Additionally, I possess exceptional skills in communication, collaboration, and technical documentation.

    Work & Experience

    D

    Data scientist/ML Project Engineer

    Jun 19 - PRESENT

    Technology

    • Icon
      MongoDB
    • Develop and deploy machine learning models and algorithms to extract insights and value from data.
    • Analyze and interpret complex data sets, and present findings to technical and non-technical stakeholders in a clear and concise manner.
    • Collaborate with cross-functional teams, including software engineers, data engineers, and business analysts, to identify opportunities for ...
    Read More

    Credit Card Prediction Based On Customer( Classification)

    Project Lead

    • Our Credit Card Prediction is a Machine Learning project based on classification techniques.
    • The first step is to clean the data using appropriate tools and technologies.
    • Business intelligence processes are applied to the cleaned data to gain insights and understanding.
    • Statistical tools are then used to analyze the features of the data.
    • Feature engineering techniques are applied to improve the accuracy of the model.
    • A classification-based algorithm is used to train the model and achieve the best accuracy.
    • Ensemble techniques are also applied to improve the accuracy of the model.
    • The final product is a Credit Card Prediction model that can accurately predict whether a credit card application will be approved or rejected.
    • python
    • pandas
    • Numpy
    • statistical tools
    • matplotlib
    • sklearn
    • emsemble techinque
    • algoritham i preferred Logistic regression
    View Details

    skin diseases classification (Deep Learning)

    Devloper

    • Developed a deep learning model for classifying skin diseases based on images of affected skin areas.
    • Used convolutional neural networks (CNNs) to process the images and extract relevant features.
    • Trained the model on a large dataset of labeled images, using techniques such as data augmentation to improve its accuracy and robustness.
    • Evaluated the performance of the model using various metrics such as accuracy, precision, recall, and F1 score.
    • Fine-tuned the model by adjusting its hyperparameters, such as learning rate, batch size, and number of layers.
    • Used transfer learning to leverage pre-trained models and improve the performance of the skin disease classification model.
    • Developed a web application to showcase the model's capabilities and allow users to upload their own images for classification.
    • Collaborated with dermatologists to validate the accuracy of the model and ensure its clinical relevance.
    • Conducted code reviews and testing to ensure the quality and reliability of the software.
    • Documented the project thoroughly, including technical specifications, user manuals, and project reports.
    • python
    • Tensorflow
    • OpenCV
    • Numpy
    • Sklearn
    • Activation Function
    • CNN
    View Details

    Natural Language Processing(Web Classification)

    part of Developer

    • In this NLP project, we followed a standard lifecycle, starting with the Exploratory Data Analysis (EDA) process.
    • During the EDA process, we used techniques such as word clouds and N-grams to gain insights into the data and identify patterns.
    • For NLP tasks, we used preprocessing techniques such as tokenization, stemming, and lemmatization to prepare the text data for analysis.
    • Next, we converted the text data into numerical or vector form using techniques such as TF-IDF and Word2Vec.
    • Finally, we used classification algorithms such as Naive Bayes to train the model and achieve an accuracy of over 80%.
    • Throughout the project, we conducted rigorous testing and validation to ensure the accuracy and reliability of the model.
    • We also documented the project thoroughly, including technical specifications, user manuals, and project reports.
    • pytho
    • tokenizer
    • porter stemmer
    • lemmatizer
    • naive bayes alogitham
    • word to vec techniques
    View Details

    Education

    N

    Bachelor of Electronics and Communication

    Nagpur University
    2012 - 2016

    Certificates

    p

    Data Scientist Certification

    pune based institute
    2018 - 2019

    Achievements

    • Working on ML project which I lead that one giving accuracy by me its 89 %.
    • Ability to understand the each and every concept