Discover @niharikabalachandra Open Source projects

Niharika Balachandra (@niharikabalachandra)

niharikabalachandra

Stars
138
Global Rank 163,793 (Top 6 %)
Followers 65
Following 12
Registered about 8 years ago
Most used languages

Jupyter Notebook
75.0 %

R
8.3 %

Python
8.3 %

MATLAB
8.3 %

Stock-Market-Prediction-Using-Natural-Language-Processing

We used Machine learning techniques to evaluate past data pertaining to the stock market and world affairs of the corresponding time period, in order to make predictions in stock trends. We built a model that will be able to buy and sell stock based on profitable prediction, without any human interactions. The model uses Natural Language Processing (NLP) to make smart “decisions” based on current affairs, article, etc. With NLP and the basic rule of probability, our goal is to increases the accuracy of the stock predictions.

Jupyter Notebook

Market-Risk-Management-with-Time-Series-Prediction-of-Stock-Market-Trends-

Market Risk Management with Time Series Prediction of Stock Market Trends using ARMA, ARIMA, GARCH regression models and RNN for time series analysis and prediction of short-term tends in stock prices.

Jupyter Notebook

Gesture-Recognition-Using-RNN

This project investigates gesture recognition techniques using Leap Motion Controller to collect 3 dimensional hand features such as coordinates, position of the hand, etc. We then use this raw data to train a Long Short Term Memory Recurrent Neural Network that is able to recognize basic hand gestures

PropensityToConvert

Propensity models make true predictions about a customer’s future behavior. With propensity models you can truly anticipate a customer's future behavior. Here we focus on building a combination of a Propensity to convert and a Propensity to buy models that can influence the kind of marketing campaigns we adopt and who we decide to target (predicted converters vs non-converters) leading to spend optimizations that eventually increase the ROI on digital marketing campaigns.

Jupyter Notebook

Language-Detection-MultinomialLogisticRegression

Language Detection using the European Parliament Proceedings Parallel Corpus. European Parliament Proceedings Parallel Corpus is a text dataset used for evaluating language detection engines. The 1.5GB corpus includes 21 languages spoken in EU. This project aims to build a machine learning model trained on this dataset to predict new unseen data.

Jupyter Notebook

Logistic-Regression-Miniproject

Logistic Regression applied on a dataset of heights and weights of males and females. The model is used for binary classification (males or females) based on the feature variables of height and weight.

Jupyter Notebook

TimeSeries-MiniProject

Dealing with time series data using pandas

Jupyter Notebook

Python-Basics

Jupyter Notebook

Multiclass-Perceptron-Training-Algorithm

Multiclass Perceptron Training Algorithm used for digit recognition

Logistic-Regression

An example that illustrates logistic regression analysis

Recommendation-Systems

Recommendation Systems for movie recommendations. Content-based filtering and Collaborative filtering evaluated using RMSE is demonstrated. Collaborative filter based on age similarities and Collaborative-based filtering using euclidean similarity functions is shown

Jupyter Notebook

Clustering-MiniProject

The dataset contains information on marketing newsletters/e-mail campaigns (e-mail offers sent to customers) and transaction level data from customers. The transactional data shows which offer customers responded to, and what the customer ended up buying. The data is presented as an Excel workbook containing two worksheets. Each worksheet contains a different dataset. We're trying to learn more about how our customers behave, so we can use their behavior (whether or not they purchased something based on an offer) as a way to group similar minded customers together. We can then study those groups to look for patterns and trends which can help us formulate future offers.

Jupyter Notebook