Challenging Japanese Stock Swing Trading with ChatGPT #37

I continue to engage in short-term swing trading, where I purchase Japanese stocks during my weekday lunch break and, in principle, sell them during the lunch break of 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 round” section, was also created by ChatGPT. The main text is organized based on actual trading records and the analysis conducted at that time.

+10,500 yen with Zensho HD! However, a cumulative deficit of over 160,000 yen across 101 trades

On October 20, I sold Zensho Holdings, which I had purchased the previous day, and locked in a profit of 10,500 yen.

Meanwhile, I newly purchased Nippon Steel and Tokyo Gas. This time, rather than growth-expectation stocks like semiconductors, the selection focused on the company’s business environment and individual factors.

1. Sold Zensho HD. Did the policy expectations continue until the next day?

[Purchased Oct 19 -> Sold Oct 20]

Zensho Holdings (7550)

• Purchase price: 12,085 yen

• Selling price: 12,190 yen

• Quantity: 100 shares

• Realized profit/loss: +10,500 yen

For Zensho HD the previous day, there was a clear factor: expectations for demand-stimulating measures in the restaurant industry.

In addition to Prime Minister Takaichi’s mention of restaurant support measures such as premium gift certificates acting as a buying factor, JCR upgraded the company’s long-term issuer rating from “A-” to “A” on October 13.

Evaluating the possibility that these policy aspects and credit improvements would support the stock price, ChatGPT identified it as a conditional buy candidate. The purchase limit was 12,100 yen, and the actual purchase price of 12,085 yen was within that range.

So, how did the price move the next day?

Against the previous day’s closing price of 12,360 yen, it opened at 12,285 yen on the 20th, and there were periods where it remained below the previous day’s closing price. The selling price was also 12,190 yen, which is below the previous day’s closing price.

The prediction of a rise from the purchase price was correct, but it was not a development where it rose strongly the next day.

Even if policy expectations and rating improvements are factors that support corporate valuation, profit-taking selling can become dominant in the short term. This time, I was able to confirm the importance of discerning not only the direction of the factors but also how long they will affect the stock price.

2. Purchased 1,000 shares of Nippon Steel. Focusing on the improvement of the steel market

[Purchased on October 20]

Nippon Steel (5401)

• 666.9 yen × 100 shares

• 666.7 yen × 900 shares

• Average acquisition price: 666.72 yen

• Total purchase amount: 666,720 yen

Regarding Nippon Steel, the improvement in U.S. steel market conditions and the inflow of funds into steel stocks were key points of interest.

U.S. steel prices are at their highest level in about four and a half years, and there was a view that tariff policies and infrastructure demand would support the market. Domestically, there were also expectations for a bottoming out of steel market conditions, and on the morning of the 20th, steel stocks such as Nippon Steel and JFE showed relatively strong movement.

While there was selling in AI-related stocks, there was also a movement of funds toward undervalued stocks that had been lagging behind.

In the ChatGPT analysis, Nippon Steel was also a conditional buy candidate. However, the extent to which the rise in steel prices will actually be reflected in corporate profits is a separate issue.

The next day, I will verify whether the inflow of funds into the steel sector continues.

3. Purchased Tokyo Gas. Targeting AI demand from the energy supply side

[Purchased on October 20]

Tokyo Gas (9531)

• Purchase price: 6,134 yen

• Quantity: 100 shares

• Total purchase amount: 613,400 yen

Tokyo Gas had new business material announced the previous day, the 19th.

The company announced the start of a collaboration with Hitachi, Ltd. and others toward the realization of a green data center with an integrated power source.

With the spread of AI, power demand for data centers is expanding. Tokyo Gas has room to be evaluated not just as a city gas supply company, but as an energy company that supports AI infrastructure.

However, this announcement concerns a business collaboration, and a concrete contribution to profits has not yet been confirmed.

ChatGPT also evaluated it as a conditional buy candidate, but whether expectations for medium- to long-term growth will lead to a stock price increase by noon the next day is the point of this verification.

4. After 101 trades. Is fundamental analysis effective for short-term trading?

The results reflecting this sale are as follows.

• Cumulative trades: 101

• 52 wins, 49 losses

• Win rate: 51.5%

• Cumulative realized profit/loss: -163,670 yen

• October realized profit/loss: -135,310 yen

*Profit/loss is before taxes and fees. Since the execution date of the 20th is not displayed in the image, it is a provisional registration date on the ledger.

Although I was able to secure a profit with Zensho HD this time, the cumulative total remains in the red.

Moving forward, I will verify whether stock selection focused on improvements in corporate performance and business environment is effective even with a short holding period until noon on the next business day.

In particular, regarding the improvement in steel market conditions for Nippon Steel and expectations for AI-related business at Tokyo Gas, whether the strength of the material matches the actual stock price reaction will be the focus next time.

Thoughts on this time

・If I make a profit of over 10,000 yen, I should probably be happy enough, but I wonder if it’s ‘stock-trader brain’ that makes me feel like it’s a modest gain. ・Looking at today’s price movement, I sold Zensho at the lowest point, which is frustrating. ・I want to short semiconductor stocks. I really want to. But I feel like if I do, that will be the bottom, so I can’t. Maybe I’ll do it tomorrow. It looks like it will fall tomorrow too. Even if I think it hit bottom, it still goes down. Long-term held semiconductor stocks too…

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

#Investment #StockInvestment #JapaneseStocks #Stocks #AssetManagement #AssetFormation #SwingTrading #InvestmentRecord #IndividualInvestor #StockInvestmentBeginner #ChatGPT #AIInvestment #FundamentalAnalysis #JapaneseStockInvestment