N.V.J.K KartikKartik

Applied research · IIT Madras · RBCDSAI · Jun 2024 · 3 months · Transformers · time series

Market sentiment

Can the mood of the market help predict it? Transformer sentiment from news and social media, next to the usual technical signals.

Plate: a price series above sentiment bars.

What I did

I ran transformer-based sentiment analysis over social media and financial news, combined it with technical indicators and fundamentals, and studied how feature selection and time-series models change prediction quality.

Who I made it with

RBCDSAI, IIT Madras.

What it’s for

A research internship at the Robert Bosch Centre for Data Science and AI, on swing trading in Indian equities.

Why it was hard

Sentiment is noisy and arrives on its own schedule. The question was whether it adds anything once price and fundamentals are already in the model.

Receipts

  1. Previous portfolio, as it stood before this redesign (self-reported)Self-reported: IIIT Dharwad (Data Science & AI), research at IIT Bombay Educational Technology, CRF approach for SSMR.

Every source on the site

Next, a little further back in timeNexus →