House Statistics Web Application (Work in Progress)• Developed a web application that provides statistics and recommendation to home buyers based on the current properties on the marketNatural Language Processing• Applied various tools and syntactic and semantic analyses, including tokenization, stop words removal, stemming, lemmatizing, bag-of-words, TF-IDM, word embedding (i.e., continuous-bag-of-words or skip gram), word2vec, and n-gramEnglish to Spanish Sequence to Sequence Translation• Developed a character-based LSTM encoder-decoder model to perform sequence to sequence predictionFake News Classification – Kaggle Competition• Developed a Passive Aggressive Classifier and an LSTM model with 94% and 92% classification accuracy on the test setSMS Spam Classification - UCI Database• Developed a Naïve Bayes Classifier with 98% classification accuracy on the test setStock Price Prediction and Forecasting• Developed a stacked LSTM model to predict and forecast stock prices by converting the price data into sequential data Image Processing• Applied various methods such as filtering, padding, thresholding, transforming, and connected-component labelingImage Classification• Developed two CNNs based on the SqueezeNet and the ResNet algorithms on the CIFAR-10 dataset using TensorFlow with 72% and 88% classification accuracyHandwritten Digit Recognition• Developed a CNN based on the LeNet-5 algorithm on the MNIST dataset using TensorFlow with 96% classification accuracyHouse Price Prediction – Kaggle Competition• Applied data visualization, outlier handling, missing value imputation, data transformation, feature engineering, and hyperparameter tuning; explored several regression models, including XGBoost and Random Forests to estimate house prices in Python with a score of 0.139 based on RMSE between the logarithm of the predicted value and the logarithm of the observed sales price