February 20, 2023
Our recent white paper illustrated that the nowcasting model with RavenPack Analytics outperforms standard approaches for asset allocation.
Thematic indicators based on RavenPack analytics have proven to be a strong asset in inflation forecasting. In our recent white paper An Inflation-based Asset Allocation Strategy with Sentiment Data, we demonstrate that sentiment based strategies outperform models that depend merely on past observed inflation, and deliver more accurate and more actionable forecasts.
While the white paper focused on the US, we talked with Fabio Franco, Senior Quantitative Researcher at RavenPack, to understand whether this approach can be replicated for predicting inflation for other economies, especially in the context of high inflation volatility .
Senior Quantitative Researcher
RavenPack
A powerful nowcasting model needs to incorporate both the slow-moving macroeconomic variables and the sentiment indicators that react quickly in response to changes in the economic outlook.
RavenPack recently published research on nowcasting US inflation. What are the challenges in trying to modelize inflation in other countries?
It depends on the country we want to predict inflation for. Some countries may have limited information in terms of data input for standard macroeconomic variables. Additionally, every economy has a different structure. In the inflation model that we use to nowcast the US inflation, we rely on a mix of standard macroeconomic variables combined with RavenPack Analytics.
However, we could also exclusively rely on RavenPack Analytics together with the machine learning (ML) approach we developed to predict inflation. Our ML model is flexible enough to adjust to various structural changes of non-US economies.
Do you see the RavenPack US inflation model extending to other economies? Are you planning to publish additional research?
We are going to improve the asset allocation strategy derived from our inflation nowcasts and extend it to other economies. In particular, we are looking to incorporate a risk control methodology into our strategy that relies on a volatility target approach.
We plan to test it on the US and the EU financial markets, by using different commodity indexes to hedge inflation.
As inflation is cooling down, would a sentiment based model be able to predict this trend accurately?
Our model has a flexible form in the sense that it can incorporate the structural changes of the economic system. Specifically, it nests a variety of models, from a simple linear model to a complex one. The model is selected by using RavenPack Analytics indicating the sentiment about the current state of the economy. This makes the model suitable to predict inflation even in periods of relative stability.
In general, with such high inflation volatility, how capable is the RavenPack model in capturing these dynamics in real time?
Our model can incorporate both the slow-moving macroeconomic variables that track the structural changes of the economic system, and the sentiment indicators that react quickly in response to changes in the economic outlook. In addition, its flexible structure that nests a variety of models makes the model suitable to predict the turning points in inflation as we factor in more uncertainty.
Please use your business email. If you don't have one, please email us at info@ravenpack.com.
We will process your personal data with the purpose of managing your personal account on RavenPack and offering our services. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability and objection by emailing us at privacy@ravenpack.com. For more information, you can check out our Privacy Policy.
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.