Ciro Gomes continues to boom. Today is election-day in Brazil. Voting is occurring. In previous elections in other countries, metrics used for election analysis have usually stabilized by this point. Not so in Brazil. The SMI of Gomes is impressively strong, far exceeding what you would expect for such a ‘forgotten’ candidate on election-day. This […]
Brazilian Election: SMI vs Polls
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) Comparing SMI and Polls Using the most recent poll data from IPESPE, we can see how poll figures and SMI ratings match up. Exhibit 1: Poll Data and SMI […]
SMI and Brazil’s Election: late 2017 to mid-2018
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) SMI and Brazil’s Election – late 2017 to mid-2018 One of the major takeaways has been the consistent strength of Bolsonaro during 2017 and 2018. His SMI, since late August […]
SMI and Brazil’s Election: early 2017 to mid-2017
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) SMI and Brazil’s Election – early 2017 to mid-2017 In July 2017, SMI forecasted two candidates as standing out of the fairly large pool of potential candidates. The first was […]
Brazil: Bolsonaro vs ‘Establishment’
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) “Establishment Politicians” Ironically, though the general sentiment is anti-establishment, this election cycle is dominated by establishment candidates. Most of the principal candidates have been on the Brazilian political scene for […]
Brazilian Election: SMI vs Prediction Markets
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) Betting / Prediction Markets In addition to polls, many analysts follow prediction or betting markets. These markets offer participants the opportunity to bet on outcomes of different events, including elections. […]
2018 Brazilian Election: Bolsonaro leads for ~ year
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) Brazil General Election 2018 In July 2017, Social Media Influence (SMI) forecasted that the then-outlier, Jair Bolsonaro, would end up winning Brazil’s presidential election. Assuming a Bolsonaro victory in the […]
SMI: Bolsonaro to win Brazilian Election
(Excerpt from a previously published report on using social media to forecast the 2018 Brazilian Presidential Election, Analyzing the 2018 Brazilian Election Social Media Influence Index, July 2018) Summary Social media based forecasting techniques are very similar to traditional polls and surveys in many ways, except that they leverage much larger sample sizes in real time and […]
SMI forecasts Italian Election, Euro to pause
We apply Social Media Influence (SMI) to the Italian Election and find out that right-leaning populist parties should outperform polls. Such unexpected outperformance should be enough to reignite risk for the Euro and Euro Assets. We expect markets to reevaluate risk / reward and to pause the past year’s appreciation. The following excerpt is taken […]
SMI Outperforms Polls in French Election
French Presidential Election SMI has lowest Forecasting Error Emmanuel Macron beat Marine Le Pen with 66.1% versus 33.9% of the popular vote, respectively. Social Media Influence (SMI) was the most accurate known forecasting method with a forecasting error of 2.7% in comparison to an average forecasting error of 4.1% for […]