Search Results

You are looking at 1 - 10 of 27 items for :

Clear All
Majid Bazarbash

predictions. ML models are designed to analyze a large amount of information contained in data from various sources. ML models could identify patterns in the data that standard econometric models cannot 3 . Nonetheless, a major shortcoming of using complex algorithms is that, in general, these patterns cannot be readily communicated with analysts and verified against expert knowledge. Therefore, while ML could make remarkable use of available data for making more accurate predictions than traditional methods, it could generate misleading results when data relevance is

Brandon Buell, Reda Cherif, Carissa Chen, Jiawen Tang, and Nils Wendt
The COVID-19 pandemic underscores the critical need for detailed, timely information on its evolving economic impacts, particularly for Sub-Saharan Africa (SSA) where data availability and lack of generalizable nowcasting methodologies limit efforts for coordinated policy responses. This paper presents a suite of high frequency and granular country-level indicator tools that can be used to nowcast GDP and track changes in economic activity for countries in SSA. We make two main contributions: (1) demonstration of the predictive power of alternative data variables such as Google search trends and mobile payments, and (2) implementation of two types of modelling methodologies, machine learning and parametric factor models, that have flexibility to incorporate mixed-frequency data variables. We present nowcast results for 2019Q4 and 2020Q1 GDP for Kenya, Nigeria, South Africa, Uganda, and Ghana, and argue that our factor model methodology can be generalized to nowcast and forecast GDP for other SSA countries with limited data availability and shorter timeframes.
Marijn A. Bolhuis and Brett Rayner

address collinearity and dimensionality problems, but do not address predictor relevance and nonlinearity problems. As a result, even state-of-the art forecasting models often result in large forecast errors. Furthermore, dynamic factor models perform particularly poorly when the variable to be predicted is volatile, such as output growth in many emerging market and developing economies. Machine learning (ML) methods present an alternative to traditional forecasting techniques . ML models can outperform traditional forecasting methods because they emphasize out

Marijn A. Bolhuis and Brett Rayner
We develop a framework to nowcast (and forecast) economic variables with machine learning techniques. We explain how machine learning methods can address common shortcomings of traditional OLS-based models and use several machine learning models to predict real output growth with lower forecast errors than traditional models. By combining multiple machine learning models into ensembles, we lower forecast errors even further. We also identify measures of variable importance to help improve the transparency of machine learning-based forecasts. Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models. The framework also better predicts economic volatility, suggesting that machine learning techniques could be an important part of the macro forecasting toolkit of many countries.
Majid Bazarbash
Recent advances in digital technology and big data have allowed FinTech (financial technology) lending to emerge as a potentially promising solution to reduce the cost of credit and increase financial inclusion. However, machine learning (ML) methods that lie at the heart of FinTech credit have remained largely a black box for the nontechnical audience. This paper contributes to the literature by discussing potential strengths and weaknesses of ML-based credit assessment through (1) presenting core ideas and the most common techniques in ML for the nontechnical audience; and (2) discussing the fundamental challenges in credit risk analysis. FinTech credit has the potential to enhance financial inclusion and outperform traditional credit scoring by (1) leveraging nontraditional data sources to improve the assessment of the borrower’s track record; (2) appraising collateral value; (3) forecasting income prospects; and (4) predicting changes in general conditions. However, because of the central role of data in ML-based analysis, data relevance should be ensured, especially in situations when a deep structural change occurs, when borrowers could counterfeit certain indicators, and when agency problems arising from information asymmetry could not be resolved. To avoid digital financial exclusion and redlining, variables that trigger discrimination should not be used to assess credit rating.
Brandon Buell, Reda Cherif, Carissa Chen, Jiawen Tang, and Nils Wendt

Country Table 2. Summary of Google Trend Search Terms Collected by Country Table 3. ML Model Timeframe, Predictors and Observation Count Table 4. Parametric Factor Model Timeframe, Predictors and Observation Count Table 5. ML Model Train and Test periods for South Africa, Kenya, and Nigeria Table 6. ML Model Predictions for YoY GDP Percent Change – Comparison with Actuals Table 7. ML Model Predictions for QoQ GDP Percent Change – Comparison with Actuals Table 8. Factor Model Estimation and Test periods for Uganda, Kenya, and Ghana Table 9. Factor Model

Brandon Buell, Reda Cherif, Carissa Chen, Jiawen Tang, and Nils Wendt

350 total data variables including alternative sources such as shipping, mobile payments, and Google Search Trends, 4 this paper presents an expanded nowcasting implementation methodology that a) enables integration of mixed frequency data (i.e., daily, weekly, monthly) and b) has flexibility to accommodate different variable update timeframes (i.e., the nowcast models can continuously update predictions as new information becomes available). For the Machine Learning (ML) models, we focus on Nigeria, Kenya, and South Africa—among the largest economies in the SSA

El Bachir Boukherouaa, Khaled AlAjmi, Jose Deodoro, Aquiles Farias, and Rangachary Ravikumar

intelligence (AI) and machine learning (ML) is changing the financial sector landscape. AI/ML facilitates enhanced capacity to predict economic, financial, and risk events; reshape financial markets; improve risk management and compliance; strengthen prudential oversight; and equip central banks with new tools to pursue their monetary and macroprudential mandates. A. Forecasting AI/ML systems are used in the financial sector to forecast macro-economic and financial variables, meet customer demands, provide payment capacity, and monitor business conditions. AI/ML models