Omicron Research Institute

QuanTek Econometrics Software

Model Portfolio

Most of the Graphs are too big to fit on the web page. So, we have provided a link to them and to other files such as Report files. To view these files in your web browser, just click the link. The files will open in their own tab in a separate web page. Then, to return to this web page, just click its tab in your browser. You can switch back and forth between tabs to compare the Graphs and Reports and then return to this web page.

Warning: The Price Projection represents the expected N-day prices.The error bars represent the expected N-day price range.  These are estimates only. It is entirely possible for prices to end up outside the expected price range at any time.

It should be emphasized that the Price Projection cannot predict every short-term fluctuation in prices. It is based on past prices only, and cannot anticipate exogenous events such as news events that influence prices. However, it seems to give predictions that are at least plausible, and over a long-term average (1024 days or 4 years), yield significant correlation with future returns, according to the correlation tests.

Disclaimer: The graphs and analysis on this and other pages of this website are for illustrative purposes only, of the QuanTek program and general principles of Econometrics. They should in no way be construed as investment advice.

Note that the QuanTek program works with any security (Stocks, Mutual Funds, ETFs, Indexes), providing analysis and information to help determine a profitable trading strategy. It does not, however, select between different securities.

Dow Industrials (.DJI) (2019-02-08)

Here is the latest shot of the Dow Jones Industrials (.DJI), on Scale 8. The support/resistance level at Dow 24,000 is shown as the green line. This shows the recent selling climax in December 2018:

Dow_1190211a

Here is another shot  of the Dow Jones Industrials (.DJI), on Scale 4. The support/resistance level at Dow 24,000 is shown as the green line. This shows the sell-off from the beginning of October to the end of December of 2018:

Dow_1190211b

Here is another shot  of the Dow Jones Industrials (.DJI), on Scale 2. The support/resistance level at Dow 24,000 is shown as the green line. This view shows how the Dow 24,000 level was a support level until recently:

Dow_1190211c

There is not much change in the Dow since last week. It appears that the recovery from the selling climax of the past few weeks is still continuing, rising above the Dow 24,000 support/resistance level. The green horizontal line at the Dow 24,000 level was the previous support level, and for a week or so served as a resistance level. Now the market is continuing to climb above this support level, returning to its long-term trend. Apparently the market has discounted all the political turmoil of the past couple of months. It also helps matters that the government shutdown ended a couple of weeks ago. However, there is another looming threat of a shutdown in a week or so, with lawmakers at an impasse, which might explain the slight downturn of the past couple of days. The first graph shows the short-term action over the past week. The third graph shows the longer-term action over the past year or so, showing how the same Dow 24,000 level was a support level back in February through July of 2018.

The second graph shows the recent sell-off that occurred over the last three months. It is curious why this occurred. The logical explanation is the unfavorable news events, culminating in the government shut-down that lasted for most of January. The economy appears to be strong and stocks are not over-valued at this point. But investors seem to be increasingly afraid of dysfunction and chaos in the government -- hence the selling climax of December. If there is any more political turmoil coming out of Washington, this could well send stocks lower again.

However, there is another interpretation of this sell-off. There has been increasing talk that the bull market is getting old and we are due for another bear market. It is the fear of a bear market that may have spooked the market and caused the selling climax. However, the market seems to have discounted this idea and all the bad news events coming out of Washington, and is now headed higher again. So maybe the sell-off from October through December, 2018, was itself the long-awaited bear market. Maybe now that the market has shaken off all the bad news, it is ready for another upleg. According to the graphs, the market has now returned to its normal long-term trend line. This is supported by the observation that the 32-day Price Projection, at 10.53%, is nearly equal to the 2048-day return, which is 10.45%.

On the other hand, there is a darker possibility. If the turmoil in Washington continues, it could be a repeat of the situation in 1974 in which there was a steep bear market. This coincided with the unfolding Watergate scandal and impeachment of President Richard Nixon, after years of unrest and conflict due to the Vietnam War. Really, I think the current situation is merely a pale reflection of that era, in which the conflicts and tensions were real and serious. But if the current situation continues to unfold and becomes more serious, it could have a similar effect on the markets.

The selling climax was actually an interesting situation, because the price action as the market was headed lower was unpredictable. The situation with the prices sharply below the mean price levels and headed down, represents a direct conflict between the two types of market correlations, namely the trend persistence, which should cause the prices to trend sharply lower, and the return-to-the-mean, which should cause the prices to reverse and trend sharply higher. At some point the latter mechanism starts to dominate over the former, and at that point the prices reverse sharply. You can see that this happened already twice previously in the recent past, once at the end of October and again near the end of November. This time the reversal was sharper than before. It resulted in a selling climax, which occurs when panic selling drives prices more and more sharply lower, so that fear dominates and builds upon itself, then suddenly greed takes over and prices rebound just as sharplyhigher. But the exact point at which this occurs is essentially unpredictable.

Much of this behavior seems to be caused by program trading. The programs sell on the way down and then buy on the way up, which creates a positive feedback loop, leading to instability in the market. This is not such a good idea -- if ordinary traders try to do it, they will probably lose money because they will be too late. A better idea is buy-low, sell-high, which creates a negative feedback loop and makes the market more stable.

Note that the Price Projection can't predict the short-term selling climax, even though we can do it ourselves to some extent. The Adaptive Filter is a Least-Mean Square filter which responds mainly to the long-term trend. This results in a prediction that resembles very closely that of the Random Walk model, which predicts the long-term trend no matter what the price level. (Of course, it is not clear which long-term trend the Random Walk model is supposed to predict.) There is just not enough data in a short-term anomaly for the filter to establish a correlation in the data, given the long-term trend which is very well-established (in the case of an index). The correlation in the long-term trend overpowers that in any short-term anomaly. So, unless the market becomes grossly over-valued or under-valued, we can expect it to return quickly to its long-term trend.

I think what we are seeing, longer-term, is a return to a more normal market, as the fiscal stimulus and low interest rates are gradually removed by the Federal Reserve. This, coupled with the political uncertainty, has been causing increased volatility over the past few months. (I think the uncertainty over our trade relations is also having an effect.)

Portfolio Report (2019-02-08)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-02-08).pdf

I did not see any good buying opportunities again this week. I strongly considered taking a profit on Boeing, given the impressive run-up it has enjoyed over the past several weeks, but finally decided against it. Boeing seems to be on a good run even though it appears to be near the top of a trading range. Looing at it over the longer term, it appears to have returned to the uptrend it has been on since January, 2018. This is corroborated by the impressive Price Projection of 37.91%. So I decided it would be a mistake to get out at this time, and that Boeing should be given more room to run.

The Model Portfolio this week is continuing to show a profit. This is due to gains in Facebook and Boeing, and a slight gain in Microsoft. Meanwhile Apple and Amazon are showing a slight loss. Tesla and JP Morgan are still showing more substantial losses.  But the remaining stocks showing a loss will probably recover shortly once the market is fully recovered from the recent sell-off. JP Morgan should do better once interest rates begin to rise. Hopefully there will be no more shocks to the market, and all of these securities can soon resume their up-trend. Let us hope there is not another government shut-down in a week or so. To go through that again might rattle the markets severely.


Portfolio Report (2019-02-01)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-02-01).pdf

I did not see any especially good buying opportunities this week. I considered taking a profit on Boeing, but finally decided against it. Boeing seems to be on a good run even though it appears to be near the top of a trading range. As for Netflix, I seriously considered buying at this point. It has not pulled back much since its steep run-up, and appears to be stable on its long-term trend curve. However, it seems a little precarious, and the Price Projection is not very favorable, at only 6.66%. This is the main reason why I did not buy at this point. Perhaps it would be better to wait for the next pull-back to buy.

The Model Portfolio this week is continuing to show a profit. This is due to gains in Facebook and Boeing, while Microsoft and Amazon are showing a slight loss. The other stocks are still below their basis price. But they will probably recover shortly once the market is fully recovered from the recent sell-off. Hopefully there will be no more shocks to the market, and all of these securities can resume their up-trend. Let us hope there is not another government shut-down in a couple of weeks. To go through that again might rattle the markets severely. (Then again, maybe the markets have already discounted that possibility. This might explain why the recovery from the selling climax has been so long and drawn-out.)

Portfolio Securities (2019-02-01)

Here are some screen shots of the QuanTek Main Graph for Netflix on all five scales (wide screen):

Figures (2019-02-01).html

Fig.1 NFLX-Netflix, Inc. (Scale 16): Netflix seems like an interesting study this week. The first graph shows NFLX on the largest scale, Scale 16. On this scale, the entire price action of the past few months does not even fit on the screen. This scale is best for checking the daily price action, which is shown by Candlesticks. Also shown are the N-day Long/Short Signals derived directly from the Price Projection, which is displayed for each day (that it is above the Threshold level) as an N-day Price Target. The Bollinger Bands are so wide that they do not even fit on the screen.

Fig.2 NFLX-Netflix, Inc. (Scale 8): On Scale 8, we begin to be able to see the complete price action for the past 8 months or so. This scale shows an intermediate-term downtrend that started in June 2018 and ended with the selling climax of December 2018. This ended in a sudden dramatic uptrend that lasted until the middle of January. Then there was a short pull-back, followed by a trend reversal to the upside a week or two ago. The Price Projection is only a meager 6.66%. This is no doubt due to the price action just described, with conflicting short-term (up), intermediate-term (down), and long-term (up) trends. This seems like a risky buy at present -- the short-term uptrend could give way once again to the intermediate-term downtrend, with a significant loss over the short-term.

Fig.3 NFLX-Netflix, Inc. (Scale 4): On Scale 4, we see the price action going back about 18 months. NFLX was in a strong uptrend until the middle of June, 2018, when it peaked and then entered its intermediate-term downtrend, lasting about 6 months until the selling climax of mid-December. The subsequent short-term uptrend starting in mid-December 2018 looks very much like the one starting in mid-December 2017. Clearly, with hind-sight the best buy opportunity would have been at the depth of the selling climax. But due to the intermediate-term downtrend, this proposition looked dubious.

Fig.4 NFLX-Netflix, Inc. (Scale 2): On Scale 2, we see the price action going back about 3 years. This shows the strong long-term uptrend that NFLX was in starting in February 2016, at the end of another selling climax that month. It appears the stock got a little ahead of itself starting in February 2018, and became overbought from February to October, 2018. On this graph, we see the long-term (robust) 2048-day Trend Line, and the 2048-day (annualized) return, which is 51.02%. So this justifies our expectation that, over the long-term, NFLX has been and will be a strong performer. However, along with the robust returns, there is also a high degree of risk, as is evident from the very wide Bollinger Bands.

Fig.5 NFLX-Netflix, Inc. (Scale 1): Finally, on Scale 1, we see the price action going back about 6 years. The entire price action is 8 years (2048 days) long, and is contained in a single graph, but I was not quite able to get the whole graph into a screen shot. This graph shows once again the long-term uptrend that NFLX has enjoyed since mid-2012. Before that, it went through some wild gyrations for a couple of years. These early gyrations no doubt account for most of the risk in the stock and the wide  Bollinger Bands. On this scale, the recent overbought condition and then the selling climax look like just minor fluctuations.In fact the overbought condition looks very much like the period from the end of 2014 to the middle of 2015, which also ended in a selling climax around August 2015. So if history repeats itself, it looks like NFLX is about to enter once again a relatively stable period of growth in another long-term uptrend, as it did from August 2015 to mid-2017.


Portfolio Report (2019-01-25)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-01-25).pdf

I have decided it is time to buy some Amazon this week. The price seems to have stabilized this past week, with no pull-back to speak of, and the Price Projection is favorable. As for Netflix, it showed only a minor pull-back last week after its very steep run-up of the previous two weeks. However, it seems a little precarious, and the Price Projection is not very favorable, although still positive. Perhaps it would be better to wait for the next pull-back to buy.

The Model Portfolio this week is continuing to show a profit. This is due to gains in Facebook, Microsoft, and Boeing, while Tesla is once again showing a loss. The other stocks are still below their basis price. But they will probably recover shortly once the market is fully recovered from the recent sell-off. Hopefully there will be no more shocks to the market, and all of these securities can resume their up-trend.

Portfolio Securities (2019-01-25)

Here are some screen shots of the QuanTek Main Graph for various securities in the Optimal Portfolio:

Figures (2019-01-25).html

Fig.1 AMZN-Amazon.com Inc. (Scale 4): Amazon looked like it was in a good position to buy, so I bought some this week. I was concerned about a possible short-term pullback, but there is no evidence of it this week and the price appears firm, at least for now. The Price Projection is a favorable 24.02%, and the Sharpe Ratio is also pretty favorable at 89.38%. The price right now appears to be very close to its long-term trend, so maybe if there is not too much turmoil out of Washington, Amazon will enter the next upleg.

Fig.2 NFLX-Netflix, Inc. (Scale 4): Netflix,appears to have undergone a slight pullback after its meteoric runup over the past couple of weeks, but less of a pullback than expected. This is somewhat worrisome, and also the Price Projection is not very good at a measly 4.93%. This stock is also very risky as can be seen from the wide Bollinger Bands and Standard Deviation of 48.07%. So I will pass for now on NFLX, but possibly buy later at a more favorable price, after the next pullback. Let's wait and see whether we have another government shutdown in three weeks!

Fig.3 MSFT-Microsoft Corporation (Scale 4): Microsoft appears stronger than some of the other stocks, as it was not affected quite so much by the recent selling climax. The Price Projection is a very healthy 41.88%, and it is sitting right on its long-term trend curve, so it neither overbought nor oversold. It also has a very respectable Sharpe Ratio of 106.77%. The risk is also low with narrow Bollinger Bands and a Standard Deviation of 21.67%. So I expect it to remain a top performer in the months to come.

Fig.4 CSCO-Cisco Systems, Inc. (Scale 4): Cisco appears to be another strong stock, although not quite as strong as MSFT. It has recovered nicely from the selling climax and shows a Price Projection of 17.20%. The Sharpe Ratio is 58.92%, respectable but not stellar. Like MSFT, this stock is sitting right on its long-term trend curve, so it neither overbought nor oversold. This looks like a good, stable stock to own, but I will wait until it is in an oversold condition to buy it.

Fig.5 JPM-JP Morgan Chase & Co. (Scale 4): JP Morgan is also recovering nicely from the recent selling climax, although it still appears somewhat oversold. Perhaps its lack of robustness is due to predictions of an economic slowdown and slower interest rate rise (which should help the bank stocks, while hurting others). This is a good stable stock, however, with narrow Bollinger Bands, a Price Projection of 18.96%, and a Sharpe Ratio of 71.62%. So it should be a good performer over the long-term, and also provide a bit of diversification for the portfolio.

Fig.6 IBM-International Business Machines (Scale 4): IBM seems to have had a rocky ride the past four months or so, since the beginning of October. It broke down seriously in October, well before the selling climax in December. Apparently it was suffering from some bad news of some sort. But last week it suddenly gapped upward, so maybe the bad news is over. This is, of course, a good, stable blue-chip stock with a long history and narrow Bollinger Bands. However, it must have been flat or negative for the past 8 years, because its Sharpe Ratio is a dismal -7.92%. Its Price Projection is also dismal at 1.78%. The stock seems to have gapped up suddenly to close to its long-term trend curve. But without any upward growth, it does not seem like much of a buy prospect, at least at this point. Maybe IBM's artificial intelligence business will eventually bring new life to its stock.


Portfolio Report (2019-01-18)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-01-18).pdf

The situation this week has not changed much from last week. The Model Portfolio this week is continuing to show a profit. This is due to gains in Facebook, Tesla, and Boeing. The other stocks are still below their basis price. But they will probably recover shortly once the market is fully recovered from the recent sell-off. Hopefully there will be no more shocks to the market, and all of these securities can resume their up-trend.

Just as last week, I don't see any good buy opportunities this week. I am still tempted to buy Amazon, due to its favorable Price Projection. However, it looks like it might be poised for another short-term down-trend. So I will wait for the next pull-back to buy this one. Netflix had a very sharp jump upward this past week. But now it is too high-priced, at least over the short-term, and poised for a possible short-term pull-back. It now has a slightly positive Price Projection. But I think it would be wise to wait to buy on the next pull-back. These are the only two stocks in the portfolio with favorable Sharpe Ratio, that I have not already bought.

Portfolio Securities (2019-01-18)

Here are some screen shots of the QuanTek Main Graph for various securities in the Optimal Portfolio:

Figures (2019-01-18).html

Fig.1 AMZN-Amazon.com Inc. (Scale 4): Amazon looks like a tempting buy at this point. It appears to be in a long-term uptrend and a short-term uptrend, but possibly in a intermediate-term downtrend. It has had an impressive short-term runup since the selling climax in mid-December. However, due to the overall downtrend since the beginning of October, the short-term uptrend could reverse and become a short-term downtrend. So it might be better to wait for a pullback, then buy in anticipation of the next market upleg (either intermediate-term or long-term).

Fig.2 NFLX-Netflix, Inc. (Scale 4): Netflix, like Amazon, appears to be in a long-term uptrend and a short-term uptrend, but possibly in a intermediate-term downtrend. In this case the intermediate-term downtrend has lasted since June-July 2018. This stock has had a meteoric runup over the past couple of weeks, more so than Amazon. It is obvious that this runup can't be sustained. There will almost certainly be a short-term pullback after such a runup. When this occurs then it might be a favorable buy opportunity, as it seems to suggest that the intermediate-term downtrend has been broken. Maybe then the stock will resume its long-term uptrend.

Fig.3 TSLA-Tesla, Inc. (Scale 2): Over the past 2048 days (8 years), Tesla has been in a long-term uptrend with an average (annualized) return of 50.18%. However, over the past 18 months or so, the stock has been in a flat trading range over the intermediate-term. This stock is also very risky, as can be seen from the very wide Bollinger Bands. So to get into this stock involved having faith that the stock would resume its rather dramatic long-term uptrend. As a matter of fact, we have already made a profit on this stock, and if it resumes its long-term uptrend, then we will be handsomely rewarded. Tesla must have run into a bit of bad news on Friday, but it is near its lower Bollinger Band, so we still think it is near a favorable long-term buy point. Maybe it will now break out of its trading range and resume its long-term uptrend once more.

Fig.4 FB-Facebook, Inc. (Scale 4): Facebook also appears to be making a nice recovery from the recent selling climax of mid-December. It also appears to be breaking out of its intermediate-term downtrend. Due to bad news over the past year, the stock is way below its Bollinger Bands, but provided we have faith that Facebook can recover from its recent troubles, we may interpret this as an extreme oversold condition. So it appears that we chose a favorable buy point for this stock, and as a result it is already showing a profit. It looks like Facebook has a long way to go to the upside, so when the market starts a new upleg, the profit potential could be substantial.  Surely this company will remain a pivotal tech company, and so I expect it to return to its former upward trend sooner or later. Notice that the Bollinger Bands are widely spaced compared to many older companies, which indicates that it is relatively volatile (hence risky).

Fig.5 AAPL-Apple Inc. (Scale 4): Apple has not made a very robust recovery from the sell-off of the past 3 months. It went from a very overbought condition in September and October to a very oversold condition now. It started to recover from the selling climax of mid-December but then stumbled. Apparently this is due to bad forecasts for sales of the i-Phone in 2019. But Apple is a great company and will no doubt recover from this news event. In fact, for the long-term, Apple  appears to be at a very favorable buy point. It appears to be trying to establish a short-term uptrend over the past couple of weeks. If this uptrend can continue, then Apple has a lot of room to run on the upside.

Fig.6 BA-The Boeing Company (Scale 4): Boeing has also had a nice runup over the past couple of weeks. This stock was much less affected by the intermediate-term downtrend than some of the others. It did go through a milder version of the recent selling climax, but since then has recovered nicely. This is a more stable and less risky stock than most of the others, as can be seen from the relatively narrow Bollinger Bands. This stock has also been in a trading range the past year or so, and currently is right in the middle of its Bollinger Bands, so we may hope that it is getting ready for a new long-term upleg. In spite of being up short-term over the past couple of weeks, the 32-day Price Projection is a healthy 36.39%, indicating that the well-established long-term trend will resume.


Portfolio Report (2019-01-11)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-01-11).pdf

The Model Portfolio this week is showing a profit once again. This is due to gains in Facebook, Tesla, and Boeing. The other stocks are still below their basis price. But they will probably recover shortly once the market is fully recovered from the recent sell-off. Hopefully there will be no more shocks to the market, and all of these securities can resume their up-trend.

I don't see any good buy opportunities this week. I am tempted to buy Amazon, due to its favorable Price Projection. However, it looks like it might be poised for another short-term down-trend. So I will wait for the next pull-back to buy this one. Netflix had a very impressive jump upward this past week. But now it is too high-priced, and poised for a possible short-term down-trend. Also it has a slightly negative Price Projection. So maybe it will be a good buy on the next pull-back.

Portfolio Securities (2019-01-11)

Here are some screen shots of the QuanTek Main Graph for the Standard & Poors 500 (.SPX). These illustrate the recent selling climax within the context of the long-term trend of the S & P 500 index, on three different scales.

Also shown are some screen shots of the QuanTek Splitter Windows for the Standard & Poors 500 (.SPX). The first two Splitter Windows represent three different Indicators, with low-pass smoothing and band-pass smoothing. The third Splitter Window shows the output of the Adaptive Filter directly and associated indicators:

Figures (2019-01-11).html

In the first two Splitter Windows, the three indicators shown are Relative Price, which is the price action relative to the 512-day smoothing curve, the Velocity, which is the returns or daily price differences, and the Volatility, which is the absolute deviation of the daily returns. All of the indicators are smoothed using N-day Wavelet Smoothing, and they are all causal (except the Range and Threshold lines themselves, which depend on taking an average over the whole indicator). The most important indicator in each case is the Relative Price. The Volatility indicator is relative to zero for Low-Pass Smoothing, but relative to its mean value for Band-Pass Smoothing.

Fig.1 .SPX-Standard & Poors 500 (Scale 8): This graph on Scale 8 shows the recent selling climax of the past several weeks. It made a partial, but not complete, recovery back to previous price levels. It appears that the recovery hit resistance at a price level about equal to the previous support level. This is probably due to the ongoing political turmoil coming out of Washington, and in particular the government shutdown, which tonight has become the longest in US history. The prices appear very oversold, being quite a bit below the Bollinger Bands. Hopefully if, and when, the political turmoil subsides, maybe the index will recover back to its long-term trend. However, note in this graph that QuanTek is giving a Buy Signal (green rectangles). This comes from the Relative Price (Low-Pass) Indicator (Fig.4) being below the Range setting, while the Adaptive Filter Output (Fig.6) is positive. In fact, the Adaptive Filter Output (Fig.6) is also above its Threshold setting, so it is also giving a Long Signal (not shown on this graph).

Fig.2 .SPX-Standard & Poors 500 (Scale 4): This graph on Scale 4 gives a little more historical perspective. Once again, the selling climax is below the outer Bollinger Band, which follows the 512-day S-G Smoothing Curve, indicating an oversold condition. Previous to that the index appeared a little overbought. On this graph are also indicated some Buy Points. These indicate inflection points in the Relative Price (Band-Pass) Indicator (Fig.5), as can be seen in Fig.5. These Buy Points are indicated by vertical green lines in all the Indicator graphs and green arrows on the Main Graph. They are triggered when the Relative Price (Band-Pass) Indicator (Fig.5) goes through a minimum outside the Range setting, while the Adaptive Filter Output (Fig.6) is positive. They indicate possible favorable buy points in case you want to time your trades, or possibly for swing trading. (Analogous statements apply to the red Sell Points.)

Fig.3 .SPX-Standard & Poors 500 (Scale 2): This graph on Scale 2 gives even more historical perspective. Also this graph is plotted relative to the 2048-day (robust) Trend Line. Relative to this long-term Trend Line the selling climax still appears to be an oversold condition. As of now, the prices have recovered back to the outer Bollinger Band, which this time follows the 2048-day Trend Line. In all these graphs, it can be seen that the Price Projection has latched on to the well-established long-term trend and is following it closely. It was not even significantly affected by the sell-off. This should be a reflection of the fact that the sell-off was just a short-term anomaly, due to exogeneous news events, which from the long-term perspective is just a minor feature of the graphs. Almost the opposite type of anomaly occurred in January, 2018 when the market became overbought for a few weeks, then recovered. From past experience we can infer that the market will probably recover and resume its upward trend within the Bollinger Bands, in a few months time.

Fig.4 .SPX-Indicators (Low-Pass Smoothing): These indicators are smoothed using Low-Pass Smoothing, similar to a moving average. The bottom indicator is Relative Price, and it serves as an indicator of overbought/oversold conditions. It can be seen that for the past couple of years, the indicator has been relatively flat, indicating that prices have stayed close to their long-term trend line. Recently, however, prices have entered an oversold condition, triggering a Buy Signal. The Range control sets the level at which Buy/Sell Signals are triggered. Note also the increased Volatility.

Fig.5 .SPX-Indicators (Band-Pass Smoothing): These indicators are smoothed using Band-Pass Smoothing, similar to the difference of two moving averages. The bottom indicator is Relative Price, and it serves as an indicator of N-day inflection points, similar to an oscillator indicator. These are shown on the graphs as the N-day Buy/Sell Points. With the recent downturn, it can be seen that this indicator shows a strong Buy Point. The Range control also sets the level at which the Buy/Sell Points are triggered. Actually, we don't use these Buy/Sell Points, but they are convenient for lining up features on the graphs. They might be useful for N-day Swing Trading, however, if you are downloading data every day.

Fig.6 .SPX-Adaptive Filter Output: These three indicators pertain to the Adaptive Filter. At the bottom is the raw output of the filter. Green indicates a positive expected return and red indicates a negative expected return. This indicator forms the basis of the Long/Short Signals. The Threshold control sets the level at which the Long/Short Signals are triggered. It can be seen that up to the present time, the Adaptive Filter has been giving a strong positive signal, which is a long indication. The middle indicator is the actual N-day 'future' returns which is the "desired output" of the Adaptive Filter. It can be seen that most of the short-term fluctuations are just stochastic noise and are not picked up in the filter output. This is also due to the fact that the LMS filter is a low-pass filter. The upper graph is the actual expected return due to the 2048-day long-term trend, extended into the future. It can be seen that the Adaptive Filter output resembles this long-term trend much more closely than it does the "desired output" that it is trying to mimick. However, it is not exactly the same, and under favorable conditions the Adaptive Filter can exceed the performance of the long-term trend. (The long-term trend is pretty good, however, over the long-term.)


Portfolio Report (2019-01-04)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2019-01-04).pdf

I don't see any good buy opportunities this week. Netflix might be a good buy eventually, but for the moment its Price Projection is still negative. It just had a sudden spike upwards, but this has happened four other times in the past couple of months, and was followed immediately by a steep decline. The trend since last June has been negative, so it might be better to wait until an intermediate-term uptrend is established. It is a similar story for Amazon and Alphabet. It might be best to wait until the government shutdown ends and the political uncertainty subsides a bit. However, our previous stock picks seem to have been pretty good. They seem to have weathered the storm pretty well -- the portfolio is down less than 2%, in spite of all the carnage.

Portfolio Securities (2019-01-04)

Here are some screen shots of the QuanTek Main Graph for various securities in the Optimal Portfolio:

Figures (2019-01-04).html

Fig.1 .GSPC-Standard & Poors 500 (Scale 8): Here is a screen shot of the S & P 500 showing, once again, the selling climax of the past couple of weeks. The light blue line is drawn at the S & P 500 2600 level, which seems to be the previous support level. Note the buy signals denoted by the green rectangles. The pattern did not make it quite back to the previous support level, unfortunately. I surmise this is due to the ongoing political uncertainty due to the government shutdown and related problems, and probably also all the talk about impeachment. But the index was up on Friday due to a better than expected employment report. The market will probably do better once all the turmoil ends, and I expect it to remain in a trading range for a year or two. Maybe then it will start a new upleg again due to new industries on the horizon, such as artificial intelligence, big data, automation, self-driving cars, clean energy, etc. My theory is that we are at the beginning of a new generational economic cycle that began around 2015, and this will power the next upleg in the market. (Of course, it is "only a theory"...)

Fig.2 AAPL-Apple Inc. (Scale 4): This shot shows the breakdown in Apple over the past couple of months, since the end of October. This seems to be due to lowered expectations for sales of the iPhone. In particular, the breakdown in the last couple of days was due to a news report of lowered expectations for iPhone sales in China. To me this seems overblown and Apple should recover from this bad news, hence now looks like a good buy opportunity. (Note the Buy Points indicated by the green arrows.) But the stock looked rather overbought from August through October, and now it is oversold, so I expect it to return to its long-term trend once the market discounts all the recent bad news events.

Fig.3 AMZN-Amazon.com Inc. (Scale 4): The graph of Amazon actually does not look too bad at this point. The Price Projection indicates a 32-day return of 24.00%. (Note that it was previously negative, a few weeks ago.) However, since September the stock has been in an intermediate-term downtrend, and if this patter were to continue it would be at a short-term peak right about now. It looks susceptible to more bad news over the short-term. However, for a long-term investor, now might be a good buy point. Given the strong long-term uptrend for this stock, it appears that the Price Projection has estimated that the positive return to the mean is stronger than the negative intermediate-term trend persistence (although it helps that the short-term trend is strongly positive). A week ago would have been a better buy point.

Fig.4 AMZN-Amazon.com Inc. (Scale 2): On this scale, the Bollinger Bands are drawn with respect to the 2048-day trend-line rather than the 512-day Smoothing Curve as on Scale 4. With respect to the long-term trend-line, the perspective looks a little different. From this perspective, it looks like Amazon was very overbought starting in January, 2018. It reached a peak in September, then broke down in the sell-off that started in October. But the recent selling climax of the past couple of weeks merely put Amazon back on the yellow trend-line once more. In other words, Amazon has merely corrected back to the price level where it should have been, if it had not become so overbought during 2018. Perhaps this is the case for the market as a whole, in which case the sell-off was merely a healthy correction back to reasonable valuations.

Fig.5 MRK-Merck & Co., Inc. (Scale 4): Merck has barely been affected by the downturn in the FANG and tech stocks over the past several months. It has been in a healthy uptrend since last Spring. It was also barely affected by the selling climax of the past couple of weeks. However, at the moment it appears somewhat overbought, at the upper range of its Bollinger Bands. Although probably a good long-term buy, at the moment it appears a little expensive. As a rule of thumb, I like to buy below the yellow curve, and sell above the yellow curve. The fact that Merck appears so favorable at the moment might mean it is near a good sell point, if an investor wanted to take some profits (and the market as a whole were at a sell point, which it isn't).

Fig.6 TGC-Tengasco Inc. (Scale 4): This is an oil/gas company, and it serves as an example of a very risky security. Note the extremely wide Bollinger Bands. You might not notice how risky this stock is, if you were to see a normal graph of it in isolation. The QuanTek graphs are all on the same (logarithmic) scale, so you can immediately notice the wide Bollinger Bands and wild behavior compared to other stocks. The most recent price was $0.99, so this qualifies as a borderline "penny stock". Typically, the lower the price, the greater the percentage swings in price, and the greater the risk. This is immediately visible on the logarithmic scale, which shows percentage changes. Note also the corresponding very wide Error Bars on the future Price Projection. You may not want to own this stock unless you are a real risk-taker!


Portfolio Report (2018-12-28)

The Optimal Portfolio we are tracking for this week is displayed in the following QuanTek Report file:

Report (2018-12-28).pdf

The market seems to have turned a corner, so it looks like a good buy opportunity right now. Actually, it would have been even better last Friday when the outlook appeared so gloomy. However, I wanted to wait until it actually turned the corner and started to exhibit upward momentum. I decided to buy 200 shares of TSLA at the close price on Friday. This is a somewhat risky stock, but had a good long-term expected return and Sharpe Ratio of 111.47%, and expected 32-day (annualized) return of 51.87%, according to the Price Projection. Some of the other stocks that might be good buys due to their low price, had a negative expected return, so TSLA was the best choice for now. Also this choice provides a little more diversification.

Portfolio Securities (2018-12-28)

Here are some screen shots of the QuanTek Main Graph for various securities in the Optimal Portfolio:

Figures (2018-12-28).html

Fig.1 TSLA-Tesla, Inc. (Scale 4): Tesla was my buy choice for this week. It has not suffered from the intermediate-term down-trend like many of the other securities, and the 32-day Price Projection is a very healthy 51.87% (annualized). This is to be contrasted with its long-term trend line which is giving a healthy 50.13% return. So the Price Projection coincides in this case with the prediction of the Random Walk model. This is a somewhat risky stock, with wide Bollinger Bands. There is no clear intermediate-term trend evident, which explains why the Price Projection has latched on to the long-term trend as the dominant trend. It appears that I got this stock at a good price, and after riding out the volatility it should give a robust long-term return.

Fig.2 NFLX-Netflix, Inc. (Scale 4): Netflix is a stock that I was considering for a buy at this time, since the price is down, but decided against it because the Price Projection is negative at -13.04% (annualized). This is to be contrasted with its long-term trend line which is giving a healthy 50.20% return. Netflix reached a peak in June and has been in a strong intermediate-term down-trend since then. Also notice that this is a rather risky stock with wide Bollinger Bands. So apparently the intermediate-term down-trend has overpowered the long-term up-trend in this case, as well as the return to the mean. The prices are still within the Bollinger Bands, so this is not a serious breakdown, but nevertheless I will wait until a positive Price Projection before I buy this stock.

Fig.3 FB-Facebook, Inc. (Scale 4): This was one of our recent buy selections, and it appears to have been a good choice. Facebook appears to be trying to recover from its dramatic down-trend starting with a serious gap in July, and establish a new up-trend. It seems to have shown some strength in the face of the recent sell-off of the past couple of weeks. This is reflected in the Price Projection, in which the return to the mean mechanism has dominated over trend persistence. In fact the Price Projection for FB corresponds more or less to its rather healthy long-term trend of 37.21%, so it is actually taking a neutral position, just as the Random Walk model would predict.

Fig.4 MSFT-Microsoft Corporation (Scale 4): Microsoft appears relatively healthy, with only a small breakdown over the past couple of months. Even during the sell-off of the past couple of weeks, it stayed within its Bollinger Bands. So the Price Projection predicts a continuation of the ongoing intermediate-term up-trend, and in fact this should surpass the long-term trend. Apparently we have a return to the mean mechanism at work, after the recent sell-off.

Fig.5 AAPL-Apple Inc. (Scale 4): This graph shows the major breakdown in AAPL since the middle of October, but it is not as bad as it seems, since AAPL started out very overbought to begin with. Now it is very oversold, but has not completely departed from the range of its Bollinger Bands (compare with GE). The Price Projection, according to trend persistence, should be strongly down, but according to return to the mean, should be strongly up. In fact, it appears to be somewhat neutral, corresponding to the average long-term trend. This is just the prediction that the Random Walk model would give. So either the Price Projection is conflicted between the two correlation mechanisms, or else it has latched on to the long-term trend, which in this case is very well established. Just as in the case of the Dow or other indexes, the long-term trend is very well established, and it is hard to believe that AAPL will stay depressed for very long. It will have a tendency to return to its long-term trend, which is what the Price Projection shows.

Fig.6 GE-General Electric Co. (Scale 4): Here is an example of a stock with a very abnormal breakdown. The price action for GE has broken down badly, having declined by over 50% in the month of October alone. The 512-day smoothing curves are curved up because, after the end of the past data, these curves are trying to make it back to the 2048-day long-term trend curve, which is far above. Notice that the Price Projection has a strong negative slope, indicating trend persistence, corresponding to the intermediate-term down-trend that has been in place since October. The Price Projection could just as easily have had a strong positive slope, indicating return to the mean, since prices are so far below their trend-lines. So this represents another conflict between the two correlation mechanisms, and in this case the trend persistence won. If the return to the mean mechanism starts to win, according to the Price Projection, then it will be a good time to buy this security.

Go back to QuanTek Home Page