Detecting and Triaging Spoofing using Temporal Convolutional Networks
By Kaushalya Kularatnam, Tania Stathaki
Rating
1424
Battle Count: 97
Relevance
8/10
Highly relevant for market makers and high-frequency traders to detect and avoid potential market manipulation
Implementation Complexity
7/10
Requires implementation of temporal convolutional networks and processing of high-frequency order book data
Reproducibility
3/5
The paper provides some details on the model architecture and dataset, but lacks specific implementation details and hyperparameters
About this paper
Methodology: Temporal Convolutional Networks with Weak Supervision. Problem types: Classification, Anomaly Detection.
The interactive Everscope explorer (charts, battles, favorites) loads below.