Language Breakdown
Lines of code distribution across 10 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in Jupyter Notebook
Collaboration Network
Global Impact visualization
Repos
15
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Boston Cartwright
@bstncartwright
Kian Bazza
@kianbazza
Luca Venir
@lucavenir
Morgan
@thehowl
Sebastián Ramírez
@tiangolo
Top Repositories
The Bitcoin currency is a publicly available, transparent, large scale network in which every single transaction can be analysed. Multiple tools are used to extract binary information, pre-process data and train machine learning models from the decentralised blockchain. As Bitcoin popularity increases both with consumers and businesses alike, this paper looks at the threat to privacy faced by users through commercial adoption by deriving user attributes, transaction properties and inherent idioms of the network. We define the Bitcoin network protocol, describe heuristics for clustering, mine the web for publicly available user information and finally train supervised learning models. We show that two machine learning algorithms perform successfully in clustering the Bitcoin transactions based on only graphical metrics measured from the transaction network. The Logistic Regression algorithm achieves an F1 score of 0.731 and the Support Vector Machines achieves an F1 score of 0.727. This work demonstrates the value of machine learning and network analysis for business intelligence; on the other hand it also reveals the potential threats to user privacy.
In auction theory, a Vickrey–Clarke–Groves (VCG) auction is a type of sealed-bid auction of multiple items. Bidders submit bids that report their valuations for the items, without knowing the bids of the other people in the auction. This code simulates an auction between bidders and available slots.
Data Mining and Information Retrieval. This project makes use of the #nowplaying dataset which can be found here. A subset of the #nowplaying dataset was extracted using Reservoir Sampling, because the original dataset was too large (13GB). More information on the sampling workflow can be found in the report, accompanying this assignment.
Predict the user’s click response to each auctioned ad impression in real-time bidding (RTB) display advertising. Specifically, given the information of the incoming bid request, the bid agent should estimate the probability that the user will click on its ad if it is displayed.
An open-source database of AI models.
Advances in deep learning had a substantial impact on the field of natural language processing in recent years. At the heart of these methods lie computational frameworks that automatically differentiate parametrized functions and learn these functions using continuous optimisation. We investigate representation learning for sentiment analysis of tweets. To this end, we will build our own simple deep learning framework and learn task-specific word and sentence representations.
Pathway databases such as Kegg, EcoCyc and MetaCyc store structured representations of known biomedical processes and make the scientist’s life easier, but are expensive to create and suffer from low coverage. This has led to major efforts in the automatic construction of such knowledge bases from natural language text. In particular, since 2009 a bi-yearly BioNLP Shared Task on “biomedical event extraction” has been held. In this task sentences are mapped to structured representations of the biomedical events they describe.
Linear and Logistic Regression Python Implementation
Open Source Impact
Contributions to external projects
