Applied collective wisdom to equity investments
I was interested in the direct use of “collective intelligence” for investment. It turns out that if you organize and summarize the opinions of many investors in a special way, you can get investment forecasts that exceed the results of the best professional analysts in their effectiveness.
For those who are curious, this is how the page with the forecasts for stocks came out, according to the collective intelligence at the moment. And the details - under the cut.
')
In recent years, many concrete examples have been accumulated of success in predicting a variety of facts based on the theory of "collective intelligence" or "wisdom of the crowd". At Google, for example, employees make predictions about events such as the launch dates of new projects and offices.
On Habré already discussed "the wisdom of the crowd" in various applications. For those who have not read these discussions, a brief summary — the theory states that, under certain conditions, a group of people can predict events better than any single expert.
Like many Russian investors, I have been watching the quotes of Russian stocks lately. Our market has lost two-thirds of capitalization in just three months, despite encouraging remarks by businessmen and politicians. At the same time, if you restore the picture of what happened bit by bit, it is clear that some experts made a fairly accurate diagnosis of what was happening and foresaw many steps of the stock market. But their voice was drowning in general information noise. In order to make predictions on stocks better, you need to find the most reasonable voices in the crowds of the crowd. In short, the idea is as follows.
People who have an idea of investing in Russian stocks, share their predictions with the community in a brief form like "Gazprom will be better than others in a few months." The task of the site is to create a transparent mechanism for identifying the best investors who regularly make correct predictions.
As an added bonus, you can create stock forecasts based on a generalized view of the entire community’s market - “collective intelligence” in action. As a result, it turns out that each member of the community can make a personal decision on investments by reviewing the forecasts of the most successful investors, as well as the generalized rating of stocks.
With a mechanism for selecting the best predictions, it was relatively simple. Since we in TIKR.ru have already adjusted the display of stock data from the RTS and MICEX exchanges, all that remained was to create a process for collecting and comparing forecasts with data about real quotes. The only less trivial question is how to compare the price of a share?
In good time for the market market index (a basket of the most significant shares) goes up. It's easy to make money these years, but it's hard to be better than the index. At such a bad time, as now, the index goes down, but not all can lose less than the index, let alone profit. Anyone can achieve “average market” returns by investing in stocks that follow the index structure, or in an index UIF. By the way, in this sense, I am amazed by the advertising of our mutual funds - they rarely compare their performance with the corresponding indices. As a result, to compare the success of forecasts in our project, the main MICEX index was chosen as the most representative index of the Russian stock market.
With the mechanism for selecting the best investors, it turned out to be a little more difficult. Initially, I wanted to make a mechanism similar to karma from Habr. But in investments, your karma, in fact, does not depend entirely on the ability to make sound judgments about investments and the votes of the community for / against your statements. A much more important investment is the ability to make a prediction on which you can earn more money than when you invest in an index.
Here I turned to the analysis of similar projects in the west. By the way, I was particularly impressed by the approach of the Microsoft investment community, CAPS MSN, created as a joint project with caps.fool.com. But at the same time I didn’t want to become a training simulator or an exchange game, because we already have a serious audience of thousands of real investors in Russian stocks.
Following the example of the listed sites, it was decided to measure the success of the investor in terms of account and accuracy. Roughly speaking, the score for each forecast is equal to the difference between stock returns and changes in the MICEX index; for each investor, the results of the forecasts are aggregated. Accuracy is the proportion of correct forecasts of the total number of investor forecasts. As a result, we get a rating of investors, and each community member sees how much better or worse his forecast is in relation to the forecasts of other participants.
For each share, all forecasts for this stock are summed up, taking into account the investor rating. It is clear that the better this investor invests in general, the greater the influence he or she has on the share rating. The resulting rank of the action reflects the collectively reasonable forecast of the community at any given moment. The direct benefit of this approach is that the process of successful investment forecasting becomes transparent to all community members, and each investor can find new investment ideas for himself, relying on collective wisdom.
It should be noted that amateurs with Habr, who know only one industry or company, can try their hand at forecasting. I will note in advance that only those users who have shared their predictions with other members of the community have access to unique aggregated results on stock forecasts. But it is possible to compete in the ability to predict with professionals - TIKR.ru contains forecasts of analysts of large investment companies, such as Unicredit Aton, Otkritie FC, BCS and others.
You can talk for a long time about the intricacies of our implementation. But in this place, I would like to invite all interested users to a joint discussion, because the exchanges will close at 18:45 and, if the forecast is made after this time, you will have to wait until the morning for the first real rating.
Most of all, how are sentences usually interested in - what can be improved, done differently? Well, the bugs, too, may have remained. I apologize in advance and promise to edit and answer questions in real time.
For those who are curious, this is how the page with the forecasts for stocks came out, according to the collective intelligence at the moment. And the details - under the cut.
')
In recent years, many concrete examples have been accumulated of success in predicting a variety of facts based on the theory of "collective intelligence" or "wisdom of the crowd". At Google, for example, employees make predictions about events such as the launch dates of new projects and offices.
On Habré already discussed "the wisdom of the crowd" in various applications. For those who have not read these discussions, a brief summary — the theory states that, under certain conditions, a group of people can predict events better than any single expert.
Like many Russian investors, I have been watching the quotes of Russian stocks lately. Our market has lost two-thirds of capitalization in just three months, despite encouraging remarks by businessmen and politicians. At the same time, if you restore the picture of what happened bit by bit, it is clear that some experts made a fairly accurate diagnosis of what was happening and foresaw many steps of the stock market. But their voice was drowning in general information noise. In order to make predictions on stocks better, you need to find the most reasonable voices in the crowds of the crowd. In short, the idea is as follows.
People who have an idea of investing in Russian stocks, share their predictions with the community in a brief form like "Gazprom will be better than others in a few months." The task of the site is to create a transparent mechanism for identifying the best investors who regularly make correct predictions.
As an added bonus, you can create stock forecasts based on a generalized view of the entire community’s market - “collective intelligence” in action. As a result, it turns out that each member of the community can make a personal decision on investments by reviewing the forecasts of the most successful investors, as well as the generalized rating of stocks.
With a mechanism for selecting the best predictions, it was relatively simple. Since we in TIKR.ru have already adjusted the display of stock data from the RTS and MICEX exchanges, all that remained was to create a process for collecting and comparing forecasts with data about real quotes. The only less trivial question is how to compare the price of a share?
In good time for the market market index (a basket of the most significant shares) goes up. It's easy to make money these years, but it's hard to be better than the index. At such a bad time, as now, the index goes down, but not all can lose less than the index, let alone profit. Anyone can achieve “average market” returns by investing in stocks that follow the index structure, or in an index UIF. By the way, in this sense, I am amazed by the advertising of our mutual funds - they rarely compare their performance with the corresponding indices. As a result, to compare the success of forecasts in our project, the main MICEX index was chosen as the most representative index of the Russian stock market.
With the mechanism for selecting the best investors, it turned out to be a little more difficult. Initially, I wanted to make a mechanism similar to karma from Habr. But in investments, your karma, in fact, does not depend entirely on the ability to make sound judgments about investments and the votes of the community for / against your statements. A much more important investment is the ability to make a prediction on which you can earn more money than when you invest in an index.
Here I turned to the analysis of similar projects in the west. By the way, I was particularly impressed by the approach of the Microsoft investment community, CAPS MSN, created as a joint project with caps.fool.com. But at the same time I didn’t want to become a training simulator or an exchange game, because we already have a serious audience of thousands of real investors in Russian stocks.
Following the example of the listed sites, it was decided to measure the success of the investor in terms of account and accuracy. Roughly speaking, the score for each forecast is equal to the difference between stock returns and changes in the MICEX index; for each investor, the results of the forecasts are aggregated. Accuracy is the proportion of correct forecasts of the total number of investor forecasts. As a result, we get a rating of investors, and each community member sees how much better or worse his forecast is in relation to the forecasts of other participants.
For each share, all forecasts for this stock are summed up, taking into account the investor rating. It is clear that the better this investor invests in general, the greater the influence he or she has on the share rating. The resulting rank of the action reflects the collectively reasonable forecast of the community at any given moment. The direct benefit of this approach is that the process of successful investment forecasting becomes transparent to all community members, and each investor can find new investment ideas for himself, relying on collective wisdom.
It should be noted that amateurs with Habr, who know only one industry or company, can try their hand at forecasting. I will note in advance that only those users who have shared their predictions with other members of the community have access to unique aggregated results on stock forecasts. But it is possible to compete in the ability to predict with professionals - TIKR.ru contains forecasts of analysts of large investment companies, such as Unicredit Aton, Otkritie FC, BCS and others.
You can talk for a long time about the intricacies of our implementation. But in this place, I would like to invite all interested users to a joint discussion, because the exchanges will close at 18:45 and, if the forecast is made after this time, you will have to wait until the morning for the first real rating.
Most of all, how are sentences usually interested in - what can be improved, done differently? Well, the bugs, too, may have remained. I apologize in advance and promise to edit and answer questions in real time.
Source: https://habr.com/ru/post/43494/
All Articles