Challenging Japanese Stock Swing Trading with ChatGPT #45

I continue to engage in short-term swing trading, where I purchase Japanese stocks during my lunch break on weekdays and, in principle, sell them during my lunch break on the next business day. I use ChatGPT for stock selection and trading decisions, verifying with my own money whether it is actually possible to make a profit in Japanese stock trading using AI.

This article, excluding the final “Thoughts on this time” section, was also created by ChatGPT. The main text is organized based on actual trading records and the analysis conducted at that time.

Profit on all 3 stocks, +33,660 yen. The biggest factor in the win was Capcom, which the AI was cautious about.

The trades on October 30th were 3 wins out of 3. I sold the 3 stocks purchased during the previous day’s lunch break and locked in a total profit of 33,660 yen. Capcom, in particular, generated 20,380 yen in profit from a single stock, driving this round’s earnings.

On the other hand, the cumulative profit/loss to date remains at minus 128,820 yen. This result shows that not only the effectiveness of AI-based stock selection, but also that the recommendation level and actual earnings do not necessarily match.

October 30th sale results

Capcom (9697)
Purchased 100 shares on October 29th at 3,731 yen and sold on the 30th at 3,934.8 yen. +20,380 yen (+5.46%).

Chugai Pharmaceutical (4519)
Purchased 100 shares on October 29th at 6,651 yen and sold on the 30th at 6,758.7 yen. +10,770 yen (+1.62%).

Nomura Holdings (8604)
Purchased 100 shares on October 29th at 1,455.4 yen and sold on the 30th at 1,480.5 yen. +2,510 yen (+1.72%).

The total realized profit is 33,660 yen. This is a significant recovery from the 19,480 yen loss incurred from two stocks the previous day.

Did the AI’s prediction hit the mark? The potential for a contrarian move shown by Capcom

In the analysis on the 29th, the stocks ChatGPT identified as conditional purchase candidates were Chugai Pharmaceutical and Nomura Holdings.

For Chugai Pharmaceutical, the increase in Core operating profit due to strong financial results was evaluated. The recovery after being sold off and the fact that the stock price was about 0.8% above the VWAP were the decision factors. The sale price the next day also exceeded the purchase price, so it can be said that the direction that the rebound after the financial results would continue until the next day was correct.

Nomura Holdings was also based on the increase in profit for the first half and the increase in the interim dividend. Since it recovered from the morning low and was above the VWAP, it was set as a purchase candidate on the condition that it maintained the recovery. This also continued to rise until the time of sale the next day.

The most interesting one is Capcom. After the sharp drop following the financial results, there were strong signs of being oversold on the RSI. However, because the reversal had not been sufficiently confirmed, the evaluation was divided by analysis, and it was excluded from the main purchase recommendations.

The result was an increase of about 5.5%. The stock that generated the largest profit this time was the one for which the AI could not sufficiently evaluate the certainty of a rebound.

While this shows the potential of a contrarian strategy, it is not proof that buying a stock that has plummeted will always result in a rebound. Since I have not verified the next day’s VWAP or high price trends, what can be confirmed at this point is the rise from the purchase price to the sale price.

4 new purchases on the 30th. Aiming for a rebound after financial results as well

On the 30th, I newly purchased the following 4 stocks.

• Hitachi, Ltd.: 100 shares, 5,024 yen

• Tokio Marine Holdings: 200 shares, 579.5 yen

• KDDI: 100 shares, 2,806 yen

• Central Japan Railway Company (JR Central): 100 shares, 3,925 yen

The total purchase amount is 1,291,400 yen.

In terms of analysis, I paid particular attention to Hitachi and JR Central. Despite strong earnings and an upward revision of its performance forecast, Hitachi saw a significant decline, so I evaluated it as a candidate for a rebound from being oversold. However, the decision was that confirmation of a recovery above the VWAP was necessary.

For JR Central, I evaluated the earnings, shareholder return policy, and the recovery in the latter half of the morning session. It was 0.34% above the VWAP, making it the top conditional purchase candidate among the 8 stocks analyzed.

Meanwhile, KDDI was marked for monitoring based on its position relative to the moving average, and Tokio Marine Holdings was passed over due to interest rate fluctuation risks. The fact that the actual purchase decisions differed from the AI’s recommendations will also be a subject for the next verification.

Total of 120 trades. The next thing to verify is the rebound strength after a sharp decline.

The cumulative results reflecting this trade are 65 wins and 55 losses out of 120 trades, with a win rate of 54.2%. The cumulative realized profit/loss is -128,820 yen. All amounts are before considering taxes, fees, etc.

This time, trades focusing on price movements after earnings announcements led to results. However, it is not yet possible to judge which is superior: the strategy of buying after strong earnings or the strategy of aiming for a rebound after a sharp decline.

The next session is November 2nd, after the weekend. I will check the results of the 4 stocks purchased this time, and continue to verify whether Hitachi’s rebound actually occurs and whether the contrarian strategy that succeeded with Capcom is a reproducible method.

Thoughts on this session

・Regarding Hitachi, which I targeted hoping for a repeat success, it looks tough based on the PTS. Or rather, it seems likely to be caught in a Black Monday scenario. Looking at Chappy’s analysis again, it suggested that it was relatively strong among the high-tech stocks that fell today, so perhaps it was a case where the price didn’t fall completely despite the bad market conditions, even though it did fall today.・Today was a rare significant positive day, recovering yesterday’s losses. However, the October total is barely a six-digit loss. If it had been just 1,000 yen more, it would have stayed at five digits.・The stability in the latter half of October was amazing, but getting hit hard somewhere and ending up in the negative is quite tough. Also, when I ignore Chappy and trade, the loss occurrence rate remains high.・Nevertheless, that is the fun of stock trading, so I want to continue intuitive trading within a reasonable range.

*This article is a record of personal trades and verification, and does not recommend buying or selling specific stocks.

#Investment #StockInvestment #JapaneseStocks #Stocks #AssetManagement #AssetFormation #SwingTrading #InvestmentRecord #IndividualInvestor #StockInvestmentBeginner #ChatGPT #AIInvestment #InvestmentBeginner #Trade #StockMarket