Featured projects

Here is a selection of projects I have recently completed. Feel free to have a look around! Alternatively, the portfolio is also available to view on Github here.

Credit card fraud: improving detection with Deep Learning

Comparing different models performance at predicting instances of fraud. The final model is a 5-layer Neural Network that correctly classifies 99.96% of transactions.

Python, Keras, Neural Network, Scikit-learn, Logistic regression, Random Forest, GridSearchCV

See project

Creating customer segments using different clustering algorithms

Unsupervised learning project in which we create clusters of customers of a wholesale distributor using algorithms such as K-means and DBSCAN.

Python, Seaborn, Box-cox transformation, PCA, K-means, Gaussian mixture, Agglomerative clustering, DBSCAN

See project

Sentiment analysis: US airlines on Twitter

Using a word embeddings approach, we analyse the sentiment of tweets regarding US airlines with different Recurrent Neural Network models: bidirectional GRU and birectional LSTM.

Python, NLP, Keras, GloVe word vectors, RNN, bidirectional GRU, bidirectional LSTM

See project

Detecting spam text messages

NLP project in which we predict whether a text message is spam or legitimate. The best performance is obtained with a Multinomial Naive Bayes model and a CountVectorizer approach.

Python, NLP, NLTK, Logistic Regression, MultinomialNB, SVC, Seaborn

See project

Predicting Boston housing prices

Using a machine learning model to predict house prices in the Boston metropolitan area. Identifying the optimal price for clients wishing to sell their home.

Python, Scikit-learn, Decision Tree regression

See project

Finding donors for a charity

In this project, we compare several algorithms in order to accurately model individuals' income and predict who is likely to become a donor.

Python, Scikit-learn, AdaBoost, SVM, Stochastic Gradient Descent Classifier

See project

Titanic dataset: exploratory analysis

Using Seaborn visualisations, this project explores the passengers' details and reveals which factors helped some of them survive the shipwreck.

Python, Pandas, Matplotlib, Seaborn

See project

Mushrooms: safe to eat or deadly?

Predicting whether mushrooms are edible or poisonous using different machine learning models.

Python, Scikit-learn, Decision Tree, Support Vector Classifier

See project