arXiv subjects

Naftali Cohen

Publications and source records attributed to Naftali Cohen.

6 recordsLinked to original sources

arXiv2025

Rethinking Beta: A Causal Take on CAPM

The CAPM regression is typically interpreted as if the market return contemporaneously \emph{causes} individual returns, motivating beta-neutral portfolios and factor attribution. For realized equity returns, however, this interpretation is inconsistent: a same-period arrow $R_{m,t} \to R_{i,t}$ conflicts with the fact that $R_m$ is itself a value-weighted aggregate of its constituents, unless $R_m$ is lagged or leave-one-out -- the ``aggregator contradiction.'' We formalize CAPM as a structural causal model and analyze the admissible three-node graphs linking an external driver $Z$, the market $R_m$, and an asset $R_i$. The empirically plausible baseline is a \emph{fork}, $Z \to \{R_m, R_i\}$, not $R_m \to R_i$. In this setting, OLS beta reflects not a causal transmission, but an attenuated proxy for how well $R_m$ captures the underlying driver $Z$. Consequently, ``beta-neutral'' portfolios can remain exposed to macro or sectoral shocks, and hedging on $R_m$ can import index-specific noise. Using stylized models and large-cap U.S.\ equity data, we show that contemporaneous betas act like proxies rather than mechanisms; any genuine market-to-stock channel, if at all, appears only at a lag and with modest economic significance. The practical message is clear: CAPM should be read as associational. Risk management and attribution should shift from fixed factor menus to explicitly declared causal paths, with ``alpha'' reserved for what remains invariant once those causal paths are explicitly blocked.

econ.TH↗

arXiv2021

Visual Time Series Forecasting: An Image-driven Approach

Time series forecasting is essential for agents to make decisions. Traditional approaches rely on statistical methods to forecast given past numeric values. In practice, end-users often rely on visualizations such as charts and plots to reason about their forecasts. Inspired by practitioners, we re-imagine the topic by creating a novel framework to produce visual forecasts, similar to the way humans intuitively do. In this work, we leverage advances in deep learning to extend the field of time series forecasting to a visual setting. We capture input data as an image and train a model to produce the subsequent image. This approach results in predicting distributions as opposed to pointwise values. We examine various synthetic and real datasets with diverse degrees of complexity. Our experiments show that visual forecasting is effective for cyclic data but somewhat less for irregular data such as stock price. Importantly, when using image-based evaluation metrics, we find the proposed visual forecasting method to outperform various numerical baselines, including ARIMA and a numerical variation of our method. We demonstrate the benefits of incorporating vision-based approaches in forecasting tasks -- both for the quality of the forecasts produced, as well as the metrics that can be used to evaluate them.

cs.CV↗

arXiv2021

Visual Time Series Forecasting: An Image-driven Approach

In this work, we address time-series forecasting as a computer vision task. We capture input data as an image and train a model to produce the subsequent image. This approach results in predicting distributions as opposed to pointwise values. To assess the robustness and quality of our approach, we examine various datasets and multiple evaluation metrics. Our experiments show that our forecasting tool is effective for cyclic data but somewhat less for irregular data such as stock prices. Importantly, when using image-based evaluation metrics, we find our method to outperform various baselines, including ARIMA, and a numerical variation of our deep learning approach.

cs.CV↗

arXiv2020

Trading via Image Classification

The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms all relying, primary, on aspects of time-series analysis. Recently, after visiting the trading floor of a leading financial institution, we noticed that traders always execute their trade orders while observing images of financial time-series on their screens. In this work, we built upon the success in image recognition and examine the value in transforming the traditional time-series analysis to that of image classification. We create a large sample of financial time-series images encoded as candlestick (Box and Whisker) charts and label the samples following three algebraically-defined binary trade strategies. Using the images, we train over a dozen machine-learning classification models and find that the algorithms are very efficient in recovering the complicated, multiscale label-generating rules when the data is represented visually. We suggest that the transformation of continuous numeric time-series classification problem to a vision problem is useful for recovering signals typical of technical analysis.

cs.CV↗

arXiv2020

What can be learned from satisfaction assessments?

Companies survey their customers to measure their satisfaction levels with the company and its services. The received responses are crucial as they allow companies to assess their respective performances and find ways to make needed improvements. This study focuses on the non-systematic bias that arises when customers assign numerical values in ordinal surveys. Using real customer satisfaction survey data of a large retail bank, we show that the common practice of segmenting ordinal survey responses into uneven segments limit the value that can be extracted from the data. We then show that it is possible to assess the magnitude of the irreducible error under simple assumptions, even in real surveys, and place the achievable modeling goal in perspective. We finish the study by suggesting that a thoughtful survey design, which uses either a careful binning strategy or proper calibration, can reduce the compounding non-systematic error even in elaborated ordinal surveys. A possible application of the calibration method we propose is efficiently conducting targeted surveys using active learning.

econ.EM↗

arXiv2019

The Effect of Visual Design in Image Classification

Financial companies continuously analyze the state of the markets to rethink and adjust their investment strategies. While the analysis is done on the digital form of data, decisions are often made based on graphical representations in white papers or presentation slides. In this study, we examine whether binary decisions are better to be decided based on the numeric or the visual representation of the same data. Using two data sets, a matrix of numerical data with spatial dependencies and financial data describing the state of the S&P index, we compare the results of supervised classification based on the original numerical representation and the visual transformation of the same data. We show that, for these data sets, the visual transformation results in higher predictability skill compared to the original form of the data. We suggest thinking of the visual representation of numeric data, effectively, as a combination of dimensional reduction and feature engineering techniques. In particular, if the visual layout encapsulates the full complexity of the data. In this view, thoughtful visual design can guard against overfitting, or introduce new features -- all of which benefit the learning process, and effectively lead to better recognition of meaningful patterns.

cs.CV↗