Course: FTEC 6V96 · Financial NLP & Textual Analysis · Author: Ashly Caicedo This project builds a story from two earlier homeworks, HW1 (a data-driven sentiment lexicon compared against TextBlob, VADER and Loughran-McDonald) and HW2 (RBM topic modelling), on a dataset of S&P 500, Dow and NASDAQ news headlines. As the assignment requires, it changes the target variable, the tokenization technique and the ML approach, and reports metrics on the train, test and inference partitions. HW1, the lexicon's edge was the market's mood. The custom lexicon beat all three benchmarks on train and test but lost on inference (0.604 vs. 0.623 precision). In October 2020 the market rose on 62% of days, and…
Independent publisher
Ashly Caicedo Cortes
AshCaiCor
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.