Algotrading in Bloomberg, R, and beyond (Financial University, Spring-Fall 2014). 

Class description: introductory course on developing trading algorithms and algotrading industry as a whole. Class is held in financial lab with 9 Bloomberg terminals; students are learning to fast-prototype algorithms using R language and real data from markets. Focus is on practice, but good understanding of underlying theory is a must. Knowledge of Bloomberg platform and R language is an advantage.

Prerequisites: basics of financial markets, technical and fundamental analysis, financial mathematics, modern portfolio theory, statistics and probability theory.

Continue reading


Application of ensemble learning for views generation in Meucci portfolio optimization framework (A.Didenko, S.Demicheva)

Modern portfolio theory assumes that decisions are made by individual agents. In reality most investors are involved in group decision-making. The paper renders group decision-making process by means of random forest algorithm, which could significantly improve prediction of weak learners by combining them into one model with superior performance. We combine technical, fundamental and sentiment analysis in order to generate views on different asset classes. Then the portfolio model is built using copula opinion-pooling under views generated by random forest. The model is backtested and results are compared with the ones obtained using traditional asset allocation techniques.

(Published in «Review of Business and Economics Studies», ISSN 2308-944X, Issue I(I) – September 2013; full text available from SSRN)

Continue reading

Multicriterial Assessment of RES- and Energy-Efficiency Promoting Policy Mixes for Russian Federation (A.Didenko)

We focus on assessing RES- and energy-efficiency promoting policy mixes for Russia from multicriteria perspective with emphasis on GHG emission reduction. We start from two surveys: the first one studies country’s energy saving and RES potential to determine possible range of outcomes for policy mixes in question; the second one reviews corpus of relevant official documents to formulate policy alternatives, which the policymakers are facing. Our findings are then blended with forecasts of government and international agencies to obtain three scenarios, describing possible joint paths of development for Russian energy sector in the context of demographic, economic and climatic trends, as well as regulatory impact from three policy portfolios, for period from 2010 (baseline year) till 2050. Scenarios are modeled in Long-Range Energy Alternatives Planning (LEAP) environment, and the output in the form of GHG emissions projections for 2010–2050 is obtained. We then assess three policy portfolios with multi-criteria climate change policies evaluation method AMS. Our analysis suggests that optimistic scenario is most environmentally friendly, pessimistic one is easier to implement, and business-as-usual balances interests of all stakeholders in charge. This might be interpreted as an evidence of lack of governmental regulation and motivation to intervene in energy sector to make it greener and more sustainable. Research was done with support of grant under European Union FP7 program PROMITHEAS-4 “Knowledge transfer and research needs for preparing mitigation/adaptation policy portfolios”.

(Published in Review of Business and Economic Sciences; full text is available at SSRN)