by Damian Grimling | Oct 7, 2022 | Sentistocks
Credit Suisse’s stock price has been on the decline for many months. Confusion over the bank’s financial condition is growing. There are further reports in the media about the potential insolvency of the institution, which is the second largest Swiss bank. Could its share price have been predicted? Yes – thanks to artificial intelligence.
Safe as a Swiss bank. Credit Suisse CDS price is a real trouble
Credit Suisse’s stock price has been on the decline for many months. As Sentimenti deals with, among other things, predicting the prices of financial instruments or cryptocurrencies, we decided to take a look at the atmosphere and mood on the web around Credit Suisse.
The analysis looked at the level of intensity of emotion and emotional arousal among authors of online opinions and comments, which were written in English and German. That’s a total of more than 40,000 mentions from May to September 2022, which our artificial intelligence looked at. The results are surprising.
It was not surprising to find a high level of intensity of emotions generally understood as negative emotions somewhat related to uncertainty (fear and sadness) or neutral emotions (surprise and anticipation). However, it was a big surprise to find an increasing level of intensity of emotions conceived as positive (trust and joy).
A detailed analysis of the content of the entries showed that the entries characterized by a high intensity of these favorable emotions are those expressing – generally speaking – satisfaction with Credit Suisse’s troubles. This state of affairs significantly affected the level of the correlation index of the intensity of emotions and the bank’s stock price.
The study of emotion diads (which form according to Pluchik’s theory) also leads to interesting observations, including showing how market attitudes changed. Thus, emotions correlated most strongly with Credit Suisse stock prices:
in May of expectation and trust – forming a diad of fatalism;
in June and July of fear and sadness – forming a diad of despair;
in August expectation and sadness – forming a diad of pessimism;
in September of expectation and disgust – forming a diad of cynicism.
Using Pearson correlation coefficient analysis, the interaction between stock prices and the intensity of emotion around Credit Suisse on the Internet was examined.
Credit Suisse problems. Are we in for a repeat of Lehman Brothers?
The analysis showed that there was a rare case where all emotions (including those considered positive) correlated negatively with Credit Suisse share prices. This meant that, in this case, a recorded increase in the intensity of emotions was linked to a decrease in share prices. In September, the strongest correlations with the share prices of Switzerland’s second largest bank were revulsion and expectation forming – according to Pluchik’s theory – a diad of cynicism.
A prototype stock price prediction model was fed for Credit Suisse with financial data (share prices) and data on the intensity of emotions, sentiment and emotional arousal around the company. A model built on an artificial neural network using BiLSTM (bidirectional long short-term memory) was used.
Using our predictive model (Sentistocks service), a success rate of up to 88% in predicting the trend of Credit Suisse’s share price over the period under study was achieved. This shows that potential investors could have successfully predicted the quotation solely on the basis of online discussions about the bank’s financial situation.
Investors remember the great collapse of Lehman Brothers. 14 years ago, it contributed to the outbreak of the global financial crisis. Will Credit Suisse face the same finale? We do not know. But the cost of CDS (insurance against bankruptcy) for the institution has approached the highest levels in almost 15 years. The bank itself foresees bumpy times ahead.
Credit Suisse CDS price. How emotions suggest the direction of a share price trend?
Sentistocks has developed effective predictive models for instruments in the cryptocurrency market. These models use both financial and emotive data to predict future prices (rates). The high success rate of the predictions developed with our tool confirms the huge role played by emotions in financial markets.
by Grzegorz Stefański | Dec 21, 2018 | Sentistocks
This time the article was prepared by Grzegorz Stefański, our financial advisor. He proposed to check whether the emotions expressed in the entries about KNF (Financial Supervision Authority) will allow to predict changes in bank indices.
In Brand24 tool we collected data from the period from 1 November to 17 December. As there was not much writing about the Supervision Authority before 13 November, we treated these 12 days as one starting point for data to which we compare further changes in sentiment and emotions expressed by Poles. As can be seen in the chart, before 13, about 200-400 mentions were written daily. On the day the scandal broke out, the number rose to over 20 800 and until today it did not fall below 700 (the least talk was about the KNF on December 5).
The banking sector on the Warsaw Stock Exchange has always been regarded as one of the more stable and relatively insensitive to sudden fluctuations. However, this stable sector is not immune to sudden turmoil, either. For nearly two months now we have been able to follow the events related to the so-called “KNF scandal”. It is clear that the situation in the KNF was very important for the banks’ listing on the WSE in the form of at least two stimulators.
The first one is media information about a conversation between the then President of the KNF and the owner of Getin Bank. The second is the detention of former members of the KNF management. It was November 13th and December 6th respectively. These events had the same resonance for the banking sector. When analysing the changes in the WIG – Banks exchange rate in that period, we notice the following reaction of the stock market with some time delay. This applies to the WIG – Banks quotation on 16 November. On that day, one of the three lowest closing prices in a year (7161.54) was recorded, while on that day the lowest price in a year (7040.86). There can be no doubt that the reason for such a significant decrease was the media information about a conversation between the then President of KNF and the owner of Getin Bank. However, the banking sector itself defended itself with results in the following days, which resulted in an increase in the exchange rate, which was not weakened by reports of the arrest of the President of KNF by law enforcement authorities (this took place on 27 November). In this period, a mini upward trend in the exchange rate is noticeable. However, further information on the arrest of former members of the PFSA management on 06 December resulted in a significant drop in quotations – to the level of 7244.17 (on 11 December).
Source: bankier.pl
The question should be asked how the bank shares market will develop further? How much more turbulence is it able to withstand without causing negative reactions from stock market investors? Analysts often use the term investor moods – but what really makes up these so-called moods? Certainly, they are positively influenced by economic results, and also undoubtedly by investment safety. But investors are people who, regardless of measurable indicators, are also guided by emotions. The stock exchange is not free of emotions – we have seen it more than once. Also, the recent events related to the PFSA had a direct impact on the banking sector listed on the WSE. These events described by the media evoked certain sentiment and emotions among the recipients, and this could undoubtedly influence their behavior, causing for example the desire to get rid of their values.
At this point it is worth analysing – as a coincidence – the changes in the intensity of sentiment in the texts on KNF compared to the changes in the WIG – Banks exchange rate between 9 November and 17 December 2018.
Source: bankier.pl / sentimenti
Analysing the above chart one can notice a certain correlation between the changes in the intensity of sentiment in the texts about KNF and the behaviour of investors manifested in the WIG – Banks exchange rate fluctuations. Thus, in a situation when the positive (increase) and negative (decrease) sentiment curves were aiming to cross, it was a certain signal to increase the bank share price. It took place on 16 November and from that day onwards the price rose until 29 November. On that day the sentimentary curves spread out and a short-term price drop was recorded. After that day, the curves entered the convergence phase again and the price went up (until 05 December). On the next day (after information about the arrest of former heads of the Polish Financial Supervision Authority), the exchange rate fell. The sentimentary curves entered a phase of retreat and the exchange rate adopted a downward trend until 11 December. After that day, the sentimentary curves came close, and the exchange rate entered the upward phase again. However, since December 13th, the positive sentiment trend has seen a decrease (and at the same time an increase in negative sentiment), and this may suggest that in the following days there may be another downward correction of bank share prices.
In this analysis, only one element has been adopted which may affect the share price levels of banks listed on the WSE. This element is media information about the situation in the PFSA. However, it already gives some premises to start observing carefully and trying to study the emotions connected with the capital market. A more complete picture can be obtained by conducting broader research, especially of the basic emotions that function in the environment of investment processes taking place on the stock exchange.
It is still necessary to consider how individual emotions have changed responding to subsequent reports of irregularities in the PFSA and whether they also have predictive power. The graph with the results of the averaged daily emotions indicates, first an increase in the proportion of disgust and anger and a decrease in joy. Strong fluctuations of trust can also be observed. SentiTool as a tool to help predict stock market trends? It seems that this is quite a possible scenario.
