English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

On a periodic basis, publicly traded companies report fundamentals, financialdata including revenue, earnings, debt, among others. Quantitative financeresearch has identified several factors, functions of the reported data thathistorically correlate with stock market performance. In this paper, we firstshow through simulation that if we could select stocks via factors calculatedon future fundamentals (via oracle), that our portfolios would far outperformstandard factor models. Motivated by this insight, we train deep nets toforecast future fundamentals from a trailing 5-year history. We proposelookahead factor models which plug these predicted future fundamentals intotraditional factors. Finally, we incorporate uncertainty estimates from bothneural heteroscedastic regression and a dropout-based heuristic, improvingperformance by adjusting our portfolios to avert risk. In retrospectiveanalysis, we leverage an industry-grade portfolio simulator (backtester) toshow simultaneous improvement in annualized return and Sharpe ratio.Specifically, the simulated annualized return for the uncertainty-aware modelis 17.7% (vs 14.0% for a standard factor model) and the Sharpe ratio is 0.84(vs 0.52).

Uncertainty-Aware Lookahead Factor Models for Quantitative Investing