[Last updated on: March, 3 2024]
Hello there, I'm Ashisha Konnur (he/him), a dedicated Data Analyst at Cognizant with a passion for refining and perfecting the world's leading navigation application 🗺️ (you know the one 😉). My academic background includes a Master's in Business Analytics from Clark University and a Bachelor's in Accounting & Finance from the University of London.
In my current role,
- I specialize in handling vast datasets, analyzing over 100,000 datapoints to conduct comprehensive statistical analyses such as ANOVA and t-tests. These analyses drive improvements in 'Point of Interest' accuracy across the several country regions within our pipeline.
- I pride myself on enhancing data accessibility and operational productivity by developing interactive dashboards in Looker Studio. These dashboards empower both management and engineering teams with actionable insights, thus facilitating informed decision-making.
Originally from 🇸🇬, I made the leap to the US in 2019, driven by a desire to pivot my career away from the volatility of the Banking and Finance industry. Witnessing colleagues face job insecurity during the pandemic reinforced my resolve. It was during this time that my interest in Data Science was sparked by my experience with the Power BI dashboard implementation at work.
I'm committed to leveraging data-driven solutions to navigate through challenges and drive innovation in the tech industry. Let's connect and explore opportunities to make impactful contributions together.✨
This repository serves to showcase my skills and as a platform to share my projects, and a way to track my progress in Data Analytics and Data Science-related topics.
-
- [Coming Soon]
In this section, I will showcase my data analytics projects, providing succinct descriptions of the technology stack employed to address various cases.
Dashboard: London Bike Share
Description: The project aims to uncover insights from the London Bike Sharing Dataset, available on Kaggle. This fascinating dataset contains a wealth of information about bike-sharing patterns in London, offering valuable insights into how weather conditions affect bike ride usage. To achieve this goal, we will use Python to directly connect to the Kaggle dataset, extract relevant metadata, and convert it into user-friendly descriptions. Furthermore, we will leverage Tableau to create an interactive dashboard that provides a comprehensive overview of the relationship between bike rides and weather changes. The project's focus on heatmaps and moving average graphs will allow for a deeper understanding of the dataset.
Skills: data cleaning, data analysis, descriptive statistics, data visualization.
Technology: Python, Pandas, Numpy, Scipy Stats, Seaborn, Matplotlib.
Dashboard: NLP with Disaster Tweets.ipynb
Description: Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time.
In this dataset, i was challenged to build a machine learning model that predicts which Tweets are about real disasters and which one’s aren’t. I had access to a dataset of 10,000 tweets that were hand classified.
Skills: NLP libraries, Text Preprocessing, Word Embeddings, Sentiment Analysis, Machine Learning, Exploratory Data Analysis
Technology: Python, Pandas, Seaborn, CountVectorizer, GloVe (ML), Baseline Model with GloVe (ML)
Dashboard: Netflix EDA.ipynb
Description: Netflix is an application that keeps growing bigger and faster with its popularity, shows and content. This is an EDA or a story telling through its data along with a content-based recommendation system and a wide range of different graphs and visuals.
Skills: Data Cleaning, Statistical Analysis, Data Visualization, Data Manipulation
Technology: Python, Matplotlib, Seaborn, Pandas
###COMING SOON
Dashboard: Stroke Prediction.ipynb
Description: Our dataset contains a total of medical records. Out of this, only records belong to patients with stroke condition, and the remaining records have no stroke condition. This is a highly unbalanced dataset.
Highlights:
• We propose a predictive analytics approach for stroke prediction.
• We use machine learning and neural networks in the proposed approach.
• We identify the most important factors for stroke prediction.
• Age, heart disease, average glucose level are important factors for predicting stroke.
• We report our results on a balanced dataset created via sub-sampling techniques.
Skills: Exploratory Data Analysis, Data Cleaning, Descriptive Analytics, Handling Imbalanced Data, Normalization
Technology: Python, Pandas, Seaborn, Decision Tree, Random Forest, Correlation Coefficient, K Means Clustering (KNN), Gaussian Naive Bayes (GNB)
- LinkedIn: @ashishakonnur