Tanjul Gohar

About Tanjul Gohar

Data enthusiast and aspiring data scientist having relevant skills in predictive modeling, data visualization, data preprocessing, and data mining algorithms to solve challenging business problems. Involved in Python open source community, SQL, and Statistics, and passionate about machine learning and deep learning. looking forward to data science opportunities. Expertise in Python, SQL, and machine learning. Looking for a chance to work on data projects.Passionate about delivering actionable insights from complex data, driving data-driven decision-making, and revolutionizing how data is used to drive cost and performance improvements.Programming Language - Database & ML Libraries Python, SQL, Pandas, NumPy, Matplotlib, Seaborn, Scikit-Learn, Keras, TensorFlow, Streamlit. Machine Learning & Deep Learning - Linear Models, Decision Tree, Ensemble Models, SVM, KNN, Naive Bayes, Clustering Algorithms, Recommendation System, ANN, CNN.Platforms - Jupyter Notebook, Google Colab, VS Code, Syder, GitHub, Git, Heroku, Excel, Streamlit.Professional Skills - Data Science, Data Analytics, ML Modelling, ML Deployment, Computer Vision, DS Consulting, Business Analytics.Key Skills : The ideal candidate will be passionate about artificial intelligence and stay up-to-date with the latest developments in the field.Analyzing and building the Client algorithms that could be used to solve a given problem and ranking them by their success probability. Also includes finding available datasets online that could be used for training.Defining the preprocessing or feature engineering to be done on a given dataset.Defining data augmentation pipelines.Training models and tuning their hyperparameters.Analyzing the errors of the model and designing strategies to overcome them.Deploying models to production.Proficiency with Python and basic libraries for machine learning such as scikit-learn and pandas.Expertise in visualizing and manipulating big datasets.Story-telling with data: strong skills in building the case for change, drawing on data and analytical techniques where appropriate, and communicating this to business audiences.Business acumen: Knowledgeable in translating business strategy into the necessary operational readiness of our systemsTechnical Knowledge: Can give comprehensive & technical specialized advice on emerging technologies. Provide guidance and counsel on complex and unfamiliar situations and leverage other experts to develop solutions.

Experience

1. Data Analyst

   Ineuron.Ai

   Nov 2022 — Present

   I am working on Retail Data Analysis Project. Introducing another Power BI Dashboard - The Retail Data Analysis- This dataset contains household-level transactions over two years from a group of 2,500 frequent shoppers at a retailer. Tools Used:Snowflake, AWS, Python, Power BI, Power BI Query. Steps I have followed :• Upload all the data sources by creating a bucket in your AWS S3 and assigning the appropriate roles and policies. Policies that allow it to access your bucket and perform such operations as creating user-specific folders and uploading data.• Then connect AWS S3 to another cloud Snowflake by creating storage integration and pipe so that continuous data upload can be tracked by creating respective tables in Snowflake.• And Create a connection between Snowflake and Jupyter Lab/notebook to retrieve the data from the tables into separate DataFrames. Perform all EDA steps, clean the tables, and store the cleaned data back into Snowflake using the snowflake-python connector in the same existing schema from where the data was extracted from the S3 bucket. To automate the EDA process and avoid running the same commands repeatedly for future data, I implemented a scheduled refresh in Jupyter Lab using jupyter_scheduler.• Create Stored Procedures and Tasks, and set the execution frequency for each table to automate the cleaning process.• And then we connect the clean data from Snowflake to Power BI where we perform all our visualization, DAX was used for creating the calculated measures and calculated column. Once done with the calculations, I made visualizations and create reports using cards, different charts, slicers etc. Which helps to easy understanding of the end-user and gives meaningful insights about the data. The pattern in Customer behavior and transaction details.Next time, if we update any further data in the source folder (S3), it will be automatically refreshed, and the report will be updated accordingly.

Education

• Jiwaji university, Gwalior Madhya Pradesh

  Master's degree

  2018 — 2020

• AlmaBetter

  Data Scientist

  2021 — 2022

• Jiwaji University

  Bachelor's degree

  2015 — 2018