or

Sergey Savastiouk, Ph.D.

Artificial Intelligence For Investments and Traders

Artificial Intelligence For Investments and Traders

Trade Ideas with Odds of Success

**Investors can use Artificial Intelligence to perform 1000+ hours of research in seconds. Learn how.**

__Learn more at Tickeron.com__

2

Traders use technical indicators like

Always remember that there is no single indicator that works well for all

Using Moving Averages to Generate Trade Ideas

But

With the creation of

No one can ever know with 100% certainty what a security's price will do from one moment to the next.

Often times, investors and traders spend lots of time accumulating fundamental and technical data about a trade, only to find themselves unsure if the trade is likely to be successful. In short, traders often have lots of great data but don't know their odds of success.

Statistics can help change this outcome. Statistics are useful in helping determine probabilities of success, by using patterns and historical outcomes (backtesting) to make projections about the future. With the help of

3

In the chapters that follow, we'll give you real examples of A.I.-generated news and trade ideas with regards to moving averages, and we'll also dig much deeper into what moving averages are and how to use them.

4

FAQ: we answer your questions posted here

A trader may now wonder: what are my odds of making a

5

Again, a trader may wonder their odds of success in trading the indicator in this case.

Here are two examples of A.I.-generated news for both the

6

Here's an example of the

A.I.dvisor looked for past instances when HURD's price movements formed a Death Cross, and found 7 cases -- 4 of which resulted in successful outcomes. Based on this data, the A.I. projects the odds of success for the trade to be 57%.

For investors and traders interested in seeing current #

For those interested in learning more about

FAQ: we answer your questions posted here

8

Trading Idea

Moving averages help mitigate noise around a financial asset, making them extremely useful for identifying trends that impact trading behavior. Two basic crossover signals – the __Golden Cross__ and __Death Cross__ – have strong predictive track records.

Day traders, will use shorter windows of time, evaluating moving averages throughout a trading day to identify and trade golden crosses – 5-period and 15-period moving averages are common for their purposes. Traders use momentum indicators like moving average convergence divergence (

For all their popularity, no golden cross is 100 percent reliable – a golden cross in unstable market conditions will not always result in a bull market, especially for single equities. Research indicates short-term gains may emerge but can be less substantial – around 1.31 percent for the 30-day period post-golden cross. 12-month average gains, however, were found to be around 11 percent.

9

The death cross accurately predicted 1929 and 2008's devastating bear markets, and savvy traders will treat them as a sign to lock in long-term gains in advance of a downturn. But death crosses do not always signal impending doom – 2018 alone saw stocks, indexes and assets like

Crossovers can also occur between short- and longterm moving averages: short-term crossing above longterm indicates a good time to buy, while short-term crossing below long-term is a sell signal. The previouslymentioned golden crosses and death crosses are two crossover signals utilizing this principle.

10

11

Envelopes are applied at an arbitrary percentage above and below the moving average line, theoretically permitting a trend to establish itself before showing buy or sell signals. A five percent envelope on a 25-day moving average would look like this:

FAQ: we answer your questions posted here

12

There are five basic kinds of moving averages:

Part of the appeal of moving averages is that they can be calculated using any time frame, depending on a trader's strategy. They are most commonly determined, however, using certain lengths, each with its own pros and cons. Traders evaluating long-term trends will be interested in 50-, 100-, and 200-day moving averages, which are less prone to temporary blips in trajectory and thus valued for their reliability. Stock traders are especially interested in 200-day averages – traders consider it a bull market period if a 50-day MA exceeds the 200-day. Inversely, a 50-day MA crossing under its 200-day counterpart usually signals a bear market.

Shorter moving averages – 5-, 10-, 20-, 30-, and, depending on context, 50-day – are valuable indicators of near-term trends. 10-day MAs, for example, are commonly used to guide intraday trading when plotted hourly. Similar to their long-term counterparts, crossover behavior of 10- and 20-day short-term MAs with a 50-day MA can also act as a harbinger of longer-term bull or bear performance.

Some traders even use__Fibonacci numbers__ – 5, 8, 13, 21, etc. – to calculate moving averages. They believe those numbers can smooth out false signals, but there is little statistical evidence to back up the practice.

Shorter moving averages – 5-, 10-, 20-, 30-, and, depending on context, 50-day – are valuable indicators of near-term trends. 10-day MAs, for example, are commonly used to guide intraday trading when plotted hourly. Similar to their long-term counterparts, crossover behavior of 10- and 20-day short-term MAs with a 50-day MA can also act as a harbinger of longer-term bull or bear performance.

Some traders even use

- Very Short Term: 5-13 days
- Short Term: 14-25 days
- Minor Intermediate: 26-49 days
- Intermediate: 50-100 days
- Long Term: 100-200 days

13

Moving averages are renowned for their malleability. This means there are plentiful types, each best applied to specific situations. We will focus on five common types of moving averages – simple; exponential; triangular; variable; and weighted – evaluating each pattern's strengths and weaknesses, how they are calculated, and what they look like when charted.

General Description

The shorter a SMA's time frame, the quicker the response to price shifts. Longer time frames react more slowly to fluctuations, delivering a flatter reading. This makes long-term SMAs strong baseline by which to measure short-term behavior, smoothing out daily ups and downs.

A single simple moving average can quickly identify the upwards or downwards trajectory of a specific asset. Combining two moving averages of different lengths, as displayed on the above chart, allows traders to view crossovers for an asset – we will further discuss how those crossover points influence trading behavior later in this ebook.

14

Also common is the __exponential moving average (EMA)__. The key difference between an exponential moving average and a simple moving average is the weight applied to recent price data – an EMA places greater emphasis on current data than an SMA, meaning exponential moving averages are more responsive to price fluctuations than SMAs.

Simple moving averages and exponential moving averages remain closely linked – so much so that the first step to calculating an EMA for an asset is to determine its SMA. The next step is to calculate the multiplier used to weight the EMA. Once both are established, the closing price-EMA from the previous day is multiplied by the weighted multiplier; the previous day's EMA is subsequently added to the result. The formula for calculating a 10-day EMA looks like this:

Simple moving averages and exponential moving averages remain closely linked – so much so that the first step to calculating an EMA for an asset is to determine its SMA. The next step is to calculate the multiplier used to weight the EMA. Once both are established, the closing price-EMA from the previous day is multiplied by the weighted multiplier; the previous day's EMA is subsequently added to the result. The formula for calculating a 10-day EMA looks like this:

Because EMAs rely heavily on past data, they become more accurate as they incorporate more data points into their calculation. They also become less agile over longer time periods, slowing under the bulk of the data used to make them. That lag is illustrated here, with the 10-day EMA closely following the price and longer-term SMAs behaving more variably:

15

The triangular moving average (TMA) is, at its basic level, a simple moving average, with one key difference – it is averaged twice. This more heavily weights the middle of a chosen time period and creates a lag in data movement.

A TMA value is first calculated by determining the SMA for an asset, then averaging the SMAs for multiple values:

A TMA value is first calculated by determining the SMA for an asset, then averaging the SMAs for multiple values:

16

The variable moving average (VMA) is a variation of the exponential moving average, created by esteemed futures trader and technical indicator developer Tushar Chande. Chande believed that an EMA could better capture (and respond to) shifting market conditions, slowing down when prices experienced a logjam but speeding back up during positive trends.

The desired response is accomplished by incorporating a volatility index into an EMA. The smoothing percentage automatically reacts in concert to volatility in a data series, shifting weight to current data in volatile situations.

The desired response is accomplished by incorporating a volatility index into an EMA. The smoothing percentage automatically reacts in concert to volatility in a data series, shifting weight to current data in volatile situations.

In this example, a 10-day VMA is calculated using a 50-day efficiency ratio as the volatility index, then plotted on a chart with a 50-day EMA:

The __weighted moving average (WMA__) is the sum of a flexible number of weighted values, each applying steadily more weight to the security in question's most recent prices (and, if desired, though far less common, the inverse). The WMA is similar in this way to an EMA, but it is calculated using a different formula:

17

18

18

Trading Idea

Sergey Savastiouk, Ph.D. has a degree in Applied Mathematics from Moscow University and has a long track record as an entrepreneur, investor, manager, and mathematician. His professional expertise is in applied mathematics, mathematical modeling, system and pattern analysis, and software and hardware system integration. He has served as CEO of several hi-tech start-up companies and nonprofit organizations, which has given him proven capabilities in business strategy for high-tech start-up companies, market assessment, company formation, team building, product development, marketing and sales. He has published numerous articles in journals and magazines on related fields. As a retail investor, he spent 15 years in the development of his proprietary trading and quantitative algorithms (now __Tickeron's A.I.__), which brought him significant returns in trading the stock market. His current work and goal in founding Tickeron is to bring professional, sophisticated stock market analysis capabilities to retail investors with an easy-to-use interface.

19

The A.I. identifies patterns by their key geometrical elements, formed by changing stock prices when plotted on a chart. The A.I. does not take into consideration stock fundamentals, expert recommendations, market conditions, and so forth. Trading in stocks and other securities involves the risk of loss.

Although our services incorporate historical financial information, past financial performance is not a guarantee or indicator of future results. Moreover, although we believe the historical information and strategies we use are reliable, we cannot guarantee them. Our services are frameworks to be used in your own investment decisions, but they are not a substitute for your own informed judgment or decisions. Moreover, they provide only some of the resources that could possibly assist you in making your decisions. You may accept, reject or modify the recommendations we provide, and you may consult with other advisors or professionals (at your expense) as you see fit regarding your personal circumstances. We do not and cannot guarantee the future performance of your investments. We do not promise that investments we recommend will be profitable. All investments are subject to various market, currency, economic, political and business risks. We do not guarantee the suitability or value of any investment information or strategy. We do not recommend any brokers or dealers for executing transactions or maintaining accounts and do not provide a mechanism for placing trades through this site. We are not responsible for advice or information you receive from anyone through the use of this site. We are not responsible for any transfers of money to any member outside of our payment system. Additional information can be found in our Terms of Use, Client Agreement, and Privacy Policy.

All graphs and data on__our website__ and marketing materials are based on simulated or hypothetical performance that have certain inherent limitations. Unlike the graphs shown in an actual performance record, these graphs do not represent actual trading. Any trades on websites are recorded paper trades and have not been executed. Simulated or hypothetical trading algorithms in general are also subject to the fact that they might be designed with the benefit of some hindsight during backtesting. No representations are made that any actual account will or is likely to achieve any profits or losses similar to these graphs or data being shown.

In addition, hypothetical trading does not involve financial risk, and no hypothetical trading can completely account for the impact of financial risk in actual trading. The ability to withstand losses are material points which can adversely affect actual trading results. There are factors related to the markets in general or to the implementation of any specific trading algorithms, which cannot be fully accounted for in the preparation of hypothetical performance results and all of which can adversely affect actual trading results.

**TRADING IS RISKY**. Past performance is not necessarily indicative of future results. Actively trading in the market may result in the losses of entire principal amount.

All graphs and data on

In addition, hypothetical trading does not involve financial risk, and no hypothetical trading can completely account for the impact of financial risk in actual trading. The ability to withstand losses are material points which can adversely affect actual trading results. There are factors related to the markets in general or to the implementation of any specific trading algorithms, which cannot be fully accounted for in the preparation of hypothetical performance results and all of which can adversely affect actual trading results.

20

The following are material assumptions used when calculating any hypothetical graphs and presenting results that appear on our__ web site:__

- Profits are reinvested. We assume profits (when there are profits) are reinvested in the trading algorithms.

- Any trading fees and commissions are not included.

- Profits are reinvested. We assume profits (when there are profits) are reinvested in the trading algorithms.

- Any trading fees and commissions are not included.

FAQ: we answer your questions posted here